Don't call readpage_end_io_hook for the btree inode. Instead of relying
on indirect calls to implement metadata buffer validation simply check
if the inode whose page we are processing equals the btree inode. If it
does call the necessary function.
This is an improvement in 2 directions:
1. We aren't paying the penalty of indirect calls in a post-speculation
attacks world.
2. The function is now named more explicitly so it's obvious what's
going on
This is in preparation to removing struct extent_io_ops altogether.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During an incremental send, when an inode has multiple new references we
might end up emitting rename operations for orphanizations that have a
source path that is no longer valid due to a previous orphanization of
some directory inode. This causes the receiver to fail since it tries
to rename a path that does not exists.
Example reproducer:
$ cat reproducer.sh
#!/bin/bash
mkfs.btrfs -f /dev/sdi >/dev/null
mount /dev/sdi /mnt/sdi
touch /mnt/sdi/f1
touch /mnt/sdi/f2
mkdir /mnt/sdi/d1
mkdir /mnt/sdi/d1/d2
# Filesystem looks like:
#
# . (ino 256)
# |----- f1 (ino 257)
# |----- f2 (ino 258)
# |----- d1/ (ino 259)
# |----- d2/ (ino 260)
btrfs subvolume snapshot -r /mnt/sdi /mnt/sdi/snap1
btrfs send -f /tmp/snap1.send /mnt/sdi/snap1
# Now do a series of changes such that:
#
# *) inode 258 has one new hardlink and the previous name changed
#
# *) both names conflict with the old names of two other inodes:
#
# 1) the new name "d1" conflicts with the old name of inode 259,
# under directory inode 256 (root)
#
# 2) the new name "d2" conflicts with the old name of inode 260
# under directory inode 259
#
# *) inodes 259 and 260 now have the old names of inode 258
#
# *) inode 257 is now located under inode 260 - an inode with a number
# smaller than the inode (258) for which we created a second hard
# link and swapped its names with inodes 259 and 260
#
ln /mnt/sdi/f2 /mnt/sdi/d1/f2_link
mv /mnt/sdi/f1 /mnt/sdi/d1/d2/f1
# Swap d1 and f2.
mv /mnt/sdi/d1 /mnt/sdi/tmp
mv /mnt/sdi/f2 /mnt/sdi/d1
mv /mnt/sdi/tmp /mnt/sdi/f2
# Swap d2 and f2_link
mv /mnt/sdi/f2/d2 /mnt/sdi/tmp
mv /mnt/sdi/f2/f2_link /mnt/sdi/f2/d2
mv /mnt/sdi/tmp /mnt/sdi/f2/f2_link
# Filesystem now looks like:
#
# . (ino 256)
# |----- d1 (ino 258)
# |----- f2/ (ino 259)
# |----- f2_link/ (ino 260)
# | |----- f1 (ino 257)
# |
# |----- d2 (ino 258)
btrfs subvolume snapshot -r /mnt/sdi /mnt/sdi/snap2
btrfs send -f /tmp/snap2.send -p /mnt/sdi/snap1 /mnt/sdi/snap2
mkfs.btrfs -f /dev/sdj >/dev/null
mount /dev/sdj /mnt/sdj
btrfs receive -f /tmp/snap1.send /mnt/sdj
btrfs receive -f /tmp/snap2.send /mnt/sdj
umount /mnt/sdi
umount /mnt/sdj
When executed the receive of the incremental stream fails:
$ ./reproducer.sh
Create a readonly snapshot of '/mnt/sdi' in '/mnt/sdi/snap1'
At subvol /mnt/sdi/snap1
Create a readonly snapshot of '/mnt/sdi' in '/mnt/sdi/snap2'
At subvol /mnt/sdi/snap2
At subvol snap1
At snapshot snap2
ERROR: rename d1/d2 -> o260-6-0 failed: No such file or directory
This happens because:
1) When processing inode 257 we end up computing the name for inode 259
because it is an ancestor in the send snapshot, and at that point it
still has its old name, "d1", from the parent snapshot because inode
259 was not yet processed. We then cache that name, which is valid
until we start processing inode 259 (or set the progress to 260 after
processing its references);
2) Later we start processing inode 258 and collecting all its new
references into the list sctx->new_refs. The first reference in the
list happens to be the reference for name "d1" while the reference for
name "d2" is next (the last element of the list).
We compute the full path "d1/d2" for this second reference and store
it in the reference (its ->full_path member). The path used for the
new parent directory was "d1" and not "f2" because inode 259, the
new parent, was not yet processed;
3) When we start processing the new references at process_recorded_refs()
we start with the first reference in the list, for the new name "d1".
Because there is a conflicting inode that was not yet processed, which
is directory inode 259, we orphanize it, renaming it from "d1" to
"o259-6-0";
4) Then we start processing the new reference for name "d2", and we
realize it conflicts with the reference of inode 260 in the parent
snapshot. So we issue an orphanization operation for inode 260 by
emitting a rename operation with a destination path of "o260-6-0"
and a source path of "d1/d2" - this source path is the value we
stored in the reference earlier at step 2), corresponding to the
->full_path member of the reference, however that path is no longer
valid due to the orphanization of the directory inode 259 in step 3).
This makes the receiver fail since the path does not exists, it should
have been "o259-6-0/d2".
Fix this by recomputing the full path of a reference before emitting an
orphanization if we previously orphanized any directory, since that
directory could be a parent in the new path. This is a rare scenario so
keeping it simple and not checking if that previously orphanized directory
is in fact an ancestor of the inode we are trying to orphanize.
A test case for fstests follows soon.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When doing an incremental send it is possible that when processing the new
references for an inode we end up issuing rename or link operations that
have an invalid path, which contains the orphanized name of a directory
before we actually orphanized it, causing the receiver to fail.
The following reproducer triggers such scenario:
$ cat reproducer.sh
#!/bin/bash
mkfs.btrfs -f /dev/sdi >/dev/null
mount /dev/sdi /mnt/sdi
touch /mnt/sdi/a
touch /mnt/sdi/b
mkdir /mnt/sdi/testdir
# We want "a" to have a lower inode number then "testdir" (257 vs 259).
mv /mnt/sdi/a /mnt/sdi/testdir/a
# Filesystem looks like:
#
# . (ino 256)
# |----- testdir/ (ino 259)
# | |----- a (ino 257)
# |
# |----- b (ino 258)
btrfs subvolume snapshot -r /mnt/sdi /mnt/sdi/snap1
btrfs send -f /tmp/snap1.send /mnt/sdi/snap1
# Now rename 259 to "testdir_2", then change the name of 257 to
# "testdir" and make it a direct descendant of the root inode (256).
# Also create a new link for inode 257 with the old name of inode 258.
# By swapping the names and location of several inodes and create a
# nasty dependency chain of rename and link operations.
mv /mnt/sdi/testdir/a /mnt/sdi/a2
touch /mnt/sdi/testdir/a
mv /mnt/sdi/b /mnt/sdi/b2
ln /mnt/sdi/a2 /mnt/sdi/b
mv /mnt/sdi/testdir /mnt/sdi/testdir_2
mv /mnt/sdi/a2 /mnt/sdi/testdir
# Filesystem now looks like:
#
# . (ino 256)
# |----- testdir_2/ (ino 259)
# | |----- a (ino 260)
# |
# |----- testdir (ino 257)
# |----- b (ino 257)
# |----- b2 (ino 258)
btrfs subvolume snapshot -r /mnt/sdi /mnt/sdi/snap2
btrfs send -f /tmp/snap2.send -p /mnt/sdi/snap1 /mnt/sdi/snap2
mkfs.btrfs -f /dev/sdj >/dev/null
mount /dev/sdj /mnt/sdj
btrfs receive -f /tmp/snap1.send /mnt/sdj
btrfs receive -f /tmp/snap2.send /mnt/sdj
umount /mnt/sdi
umount /mnt/sdj
When running the reproducer, the receive of the incremental send stream
fails:
$ ./reproducer.sh
Create a readonly snapshot of '/mnt/sdi' in '/mnt/sdi/snap1'
At subvol /mnt/sdi/snap1
Create a readonly snapshot of '/mnt/sdi' in '/mnt/sdi/snap2'
At subvol /mnt/sdi/snap2
At subvol snap1
At snapshot snap2
ERROR: link b -> o259-6-0/a failed: No such file or directory
The problem happens because of the following:
1) Before we start iterating the list of new references for inode 257,
we generate its current path and store it at @valid_path, done at
the very beginning of process_recorded_refs(). The generated path
is "o259-6-0/a", containing the orphanized name for inode 259;
2) Then we iterate over the list of new references, which has the
references "b" and "testdir" in that specific order;
3) We process reference "b" first, because it is in the list before
reference "testdir". We then issue a link operation to create
the new reference "b" using a target path corresponding to the
content at @valid_path, which corresponds to "o259-6-0/a".
However we haven't yet orphanized inode 259, its name is still
"testdir", and not "o259-6-0". The orphanization of 259 did not
happen yet because we will process the reference named "testdir"
for inode 257 only in the next iteration of the loop that goes
over the list of new references.
Fix the issue by having a preliminar iteration over all the new references
at process_recorded_refs(). This iteration is responsible only for doing
the orphanization of other inodes that have and old reference that
conflicts with one of the new references of the inode we are currently
processing. The emission of rename and link operations happen now in the
next iteration of the new references.
A test case for fstests will follow soon.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Commit 259ee7754b ("btrfs: tree-checker: Add ROOT_ITEM check")
introduced btrfs root item size check, however btrfs root item has two
versions, the legacy one which just ends before generation_v2 member, is
smaller than current btrfs root item size.
This caused btrfs kernel to reject valid but old tree root leaves.
Fix this problem by also allowing legacy root item, since kernel can
already handle them pretty well and upgrade to newer root item format
when needed.
Reported-by: Martin Steigerwald <martin@lichtvoll.de>
Fixes: 259ee7754b ("btrfs: tree-checker: Add ROOT_ITEM check")
CC: stable@vger.kernel.org # 5.4+
Tested-By: Martin Steigerwald <martin@lichtvoll.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In the definitions generated by BTRFS_SETGET_HEADER_FUNCS there's direct
pointer assignment but we should use the helpers for unaligned access
for clarity. It hasn't been a problem so far because of the natural
alignment.
Similarly for BTRFS_SETGET_STACK_FUNCS, that usually get a structure
from stack that has an aligned start but some members may not be aligned
due to packing. This as well hasn't caused problems so far.
Move the put/get_unaligned_le8 stubs to ctree.h so we can use them.
Signed-off-by: David Sterba <dsterba@suse.com>
The free space inode stores the tracking data, checksums etc, using the
io_ctl structure and moving the pointers. The data are generally aligned
to at least 4 bytes (u32 for CRC) so it's not completely unaligned but
for clarity we should use the proper helpers whenever a struct is
initialized from io_ctl->cur pointer.
Signed-off-by: David Sterba <dsterba@suse.com>
The header is mapped onto the send buffer and thus its members may be
potentially unaligned so use the helpers instead of directly assigning
the pointers. This has worked so far but let's use the helpers to make
that clear.
Signed-off-by: David Sterba <dsterba@suse.com>
Btree inode is special compared to all other inode extent io_trees,
although it has a btrfs inode, it doesn't have the track_uptodate bit at
all.
This means a lot of things like extent locking doesn't even need to be
applied to btree io tree.
Since it's so special, adds a new owner value for it to make debuging a
little easier.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Replace kvzalloc() call with kvcalloc() that also checks the size
internally. There's a standalone overflow check in the function so we
can return invalid parameter combination. Use array_size() helper to
compute the memory size for clone_sources_tmp.
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Denis Efremov <efremov@linux.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
btrfs_ioctl_send() used open-coded kvzalloc implementation earlier.
The code was accidentally replaced with kzalloc() call [1]. Restore
the original code by using kvzalloc() to allocate sctx->clone_roots.
[1] https://patchwork.kernel.org/patch/9757891/#20529627
Fixes: 818e010bf9 ("btrfs: replace opencoded kvzalloc with the helper")
CC: stable@vger.kernel.org # 4.14+
Signed-off-by: Denis Efremov <efremov@linux.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The passed in ordered_extent struct is always well-formed and contains
the inode making the explicit argument redundant.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It's used to reference the csum root which can be done from the trans
handle as well. Simplify the signature and while at it also remove the
noinline attribute as the function uses only at most 16 bytes of stack
space.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This makes reading the code a tad easier by decreasing the level of
indirection by one.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It's always set to 0 by the 2 callers so move it inside __do_readpage.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It's always set to 0 by its sole caller - btrfs_readpage. Simply remove
it.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It's always set to 0 from the sole caller - btrfs_readpage.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that btrfs_readpage is the only caller of extent_read_full_page the
latter can be open coded in the former. Use the occassion to rename
__extent_read_full_page to extent_read_full_page. To facillitate this
change submit_one_bio has to be exported as well.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It's called only from btrfs_readpage which always passes 0 so just sink
the argument into extent_read_full_page.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that this function is only responsible for reading data pages it's
no longer necessary to pass get_extent_t parameter across several
layers of functions. This patch removes this parameter from multiple
functions: __get_extent_map/__do_readpage/__extent_read_full_page/
extent_read_full_page and simply calls btrfs_get_extent directly in
__get_extent_map.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The sole purpose of this function was to satisfy the requirements of
__do_readpage. Since that function is no longer used to read metadata
pages the need to keep btree_get_extent around has also disappeared.
Simply remove it.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Metadata pages currently use __do_readpage to read metadata pages,
unfortunately this function is also used to deal with ordinary data
pages. This makes the metadata pages reading code to go through multiple
hoops in order to adhere to __do_readpage invariants. Most of these are
necessary for data pages which could be compressed. For metadata it's
enough to simply build a bio and submit it.
To this effect simply call submit_extent_page directly from
read_extent_buffer_pages which is the only callpath used to populate
extent_buffers with data. This in turn enables further cleanups.
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There is no way for this function to be called as ->readpage() since
it's called from
generic_file_buffered_read/filemap_fault/do_read_cache_page/readhead
code. BTRFS doesn't utilize the first 3 for the btree inode and
implements it's owon readhead mechanism. So simply remove the function.
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Logging directories with many entries can take a significant amount of
time, and in some cases monopolize a cpu/core for a long time if the
logging task doesn't happen to block often enough.
Johannes and Lu Fengqi reported test case generic/041 triggering a soft
lockup when the kernel has CONFIG_SOFTLOCKUP_DETECTOR=y. For this test
case we log an inode with 3002 hard links, and because the test removed
one hard link before fsyncing the file, the inode logging causes the
parent directory do be logged as well, which has 6004 directory items to
log (3002 BTRFS_DIR_ITEM_KEY items plus 3002 BTRFS_DIR_INDEX_KEY items),
so it can take a significant amount of time and trigger the soft lockup.
So just make tree-log.c:log_dir_items() reschedule when necessary,
releasing the current search path before doing so and then resume from
where it was before the reschedule.
The stack trace produced when the soft lockup happens is the following:
[10480.277653] watchdog: BUG: soft lockup - CPU#2 stuck for 22s! [xfs_io:28172]
[10480.279418] Modules linked in: dm_thin_pool dm_persistent_data (...)
[10480.284915] irq event stamp: 29646366
[10480.285987] hardirqs last enabled at (29646365): [<ffffffff85249b66>] __slab_alloc.constprop.0+0x56/0x60
[10480.288482] hardirqs last disabled at (29646366): [<ffffffff8579b00d>] irqentry_enter+0x1d/0x50
[10480.290856] softirqs last enabled at (4612): [<ffffffff85a00323>] __do_softirq+0x323/0x56c
[10480.293615] softirqs last disabled at (4483): [<ffffffff85800dbf>] asm_call_on_stack+0xf/0x20
[10480.296428] CPU: 2 PID: 28172 Comm: xfs_io Not tainted 5.9.0-rc4-default+ #1248
[10480.298948] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba527-rebuilt.opensuse.org 04/01/2014
[10480.302455] RIP: 0010:__slab_alloc.constprop.0+0x19/0x60
[10480.304151] Code: 86 e8 31 75 21 00 66 66 2e 0f 1f 84 00 00 00 (...)
[10480.309558] RSP: 0018:ffffadbe09397a58 EFLAGS: 00000282
[10480.311179] RAX: ffff8a495ab92840 RBX: 0000000000000282 RCX: 0000000000000006
[10480.313242] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff85249b66
[10480.315260] RBP: ffff8a497d04b740 R08: 0000000000000001 R09: 0000000000000001
[10480.317229] R10: ffff8a497d044800 R11: ffff8a495ab93c40 R12: 0000000000000000
[10480.319169] R13: 0000000000000000 R14: 0000000000000c40 R15: ffffffffc01daf70
[10480.321104] FS: 00007fa1dc5c0e40(0000) GS:ffff8a497da00000(0000) knlGS:0000000000000000
[10480.323559] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[10480.325235] CR2: 00007fa1dc5befb8 CR3: 0000000004f8a006 CR4: 0000000000170ea0
[10480.327259] Call Trace:
[10480.328286] ? overwrite_item+0x1f0/0x5a0 [btrfs]
[10480.329784] __kmalloc+0x831/0xa20
[10480.331009] ? btrfs_get_32+0xb0/0x1d0 [btrfs]
[10480.332464] overwrite_item+0x1f0/0x5a0 [btrfs]
[10480.333948] log_dir_items+0x2ee/0x570 [btrfs]
[10480.335413] log_directory_changes+0x82/0xd0 [btrfs]
[10480.336926] btrfs_log_inode+0xc9b/0xda0 [btrfs]
[10480.338374] ? init_once+0x20/0x20 [btrfs]
[10480.339711] btrfs_log_inode_parent+0x8d3/0xd10 [btrfs]
[10480.341257] ? dget_parent+0x97/0x2e0
[10480.342480] btrfs_log_dentry_safe+0x3a/0x50 [btrfs]
[10480.343977] btrfs_sync_file+0x24b/0x5e0 [btrfs]
[10480.345381] do_fsync+0x38/0x70
[10480.346483] __x64_sys_fsync+0x10/0x20
[10480.347703] do_syscall_64+0x2d/0x70
[10480.348891] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[10480.350444] RIP: 0033:0x7fa1dc80970b
[10480.351642] Code: 0f 05 48 3d 00 f0 ff ff 77 45 c3 0f 1f 40 00 48 (...)
[10480.356952] RSP: 002b:00007fffb3d081d0 EFLAGS: 00000293 ORIG_RAX: 000000000000004a
[10480.359458] RAX: ffffffffffffffda RBX: 0000562d93d45e40 RCX: 00007fa1dc80970b
[10480.361426] RDX: 0000562d93d44ab0 RSI: 0000562d93d45e60 RDI: 0000000000000003
[10480.363367] RBP: 0000000000000001 R08: 0000000000000000 R09: 00007fa1dc7b2a40
[10480.365317] R10: 0000562d93d0e366 R11: 0000000000000293 R12: 0000000000000001
[10480.367299] R13: 0000562d93d45290 R14: 0000562d93d45e40 R15: 0000562d93d45e60
Link: https://lore.kernel.org/linux-btrfs/20180713090216.GC575@fnst.localdomain/
Reported-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
CC: stable@vger.kernel.org # 4.4+
Tested-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
While running xfstests btrfs/177 I got the following lockdep splat
======================================================
WARNING: possible circular locking dependency detected
5.9.0-rc3+ #5 Not tainted
------------------------------------------------------
kswapd0/100 is trying to acquire lock:
ffff97066aa56760 (&delayed_node->mutex){+.+.}-{3:3}, at: __btrfs_release_delayed_node.part.0+0x3f/0x330
but task is already holding lock:
ffffffff9fd74700 (fs_reclaim){+.+.}-{0:0}, at: __fs_reclaim_acquire+0x5/0x30
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #3 (fs_reclaim){+.+.}-{0:0}:
fs_reclaim_acquire+0x65/0x80
slab_pre_alloc_hook.constprop.0+0x20/0x200
kmem_cache_alloc+0x37/0x270
alloc_inode+0x82/0xb0
iget_locked+0x10d/0x2c0
kernfs_get_inode+0x1b/0x130
kernfs_get_tree+0x136/0x240
sysfs_get_tree+0x16/0x40
vfs_get_tree+0x28/0xc0
path_mount+0x434/0xc00
__x64_sys_mount+0xe3/0x120
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xa9
-> #2 (kernfs_mutex){+.+.}-{3:3}:
__mutex_lock+0x7e/0x7e0
kernfs_add_one+0x23/0x150
kernfs_create_dir_ns+0x7a/0xb0
sysfs_create_dir_ns+0x60/0xb0
kobject_add_internal+0xc0/0x2c0
kobject_add+0x6e/0x90
btrfs_sysfs_add_block_group_type+0x102/0x160
btrfs_make_block_group+0x167/0x230
btrfs_alloc_chunk+0x54f/0xb80
btrfs_chunk_alloc+0x18e/0x3a0
find_free_extent+0xdf6/0x1210
btrfs_reserve_extent+0xb3/0x1b0
btrfs_alloc_tree_block+0xb0/0x310
alloc_tree_block_no_bg_flush+0x4a/0x60
__btrfs_cow_block+0x11a/0x530
btrfs_cow_block+0x104/0x220
btrfs_search_slot+0x52e/0x9d0
btrfs_insert_empty_items+0x64/0xb0
btrfs_new_inode+0x225/0x730
btrfs_create+0xab/0x1f0
lookup_open.isra.0+0x52d/0x690
path_openat+0x2a7/0x9e0
do_filp_open+0x75/0x100
do_sys_openat2+0x7b/0x130
__x64_sys_openat+0x46/0x70
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xa9
-> #1 (&fs_info->chunk_mutex){+.+.}-{3:3}:
__mutex_lock+0x7e/0x7e0
btrfs_chunk_alloc+0x125/0x3a0
find_free_extent+0xdf6/0x1210
btrfs_reserve_extent+0xb3/0x1b0
btrfs_alloc_tree_block+0xb0/0x310
alloc_tree_block_no_bg_flush+0x4a/0x60
__btrfs_cow_block+0x11a/0x530
btrfs_cow_block+0x104/0x220
btrfs_search_slot+0x52e/0x9d0
btrfs_lookup_inode+0x2a/0x8f
__btrfs_update_delayed_inode+0x80/0x240
btrfs_commit_inode_delayed_inode+0x119/0x120
btrfs_evict_inode+0x357/0x500
evict+0xcf/0x1f0
do_unlinkat+0x1a9/0x2b0
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xa9
-> #0 (&delayed_node->mutex){+.+.}-{3:3}:
__lock_acquire+0x119c/0x1fc0
lock_acquire+0xa7/0x3d0
__mutex_lock+0x7e/0x7e0
__btrfs_release_delayed_node.part.0+0x3f/0x330
btrfs_evict_inode+0x24c/0x500
evict+0xcf/0x1f0
dispose_list+0x48/0x70
prune_icache_sb+0x44/0x50
super_cache_scan+0x161/0x1e0
do_shrink_slab+0x178/0x3c0
shrink_slab+0x17c/0x290
shrink_node+0x2b2/0x6d0
balance_pgdat+0x30a/0x670
kswapd+0x213/0x4c0
kthread+0x138/0x160
ret_from_fork+0x1f/0x30
other info that might help us debug this:
Chain exists of:
&delayed_node->mutex --> kernfs_mutex --> fs_reclaim
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(fs_reclaim);
lock(kernfs_mutex);
lock(fs_reclaim);
lock(&delayed_node->mutex);
*** DEADLOCK ***
3 locks held by kswapd0/100:
#0: ffffffff9fd74700 (fs_reclaim){+.+.}-{0:0}, at: __fs_reclaim_acquire+0x5/0x30
#1: ffffffff9fd65c50 (shrinker_rwsem){++++}-{3:3}, at: shrink_slab+0x115/0x290
#2: ffff9706629780e0 (&type->s_umount_key#36){++++}-{3:3}, at: super_cache_scan+0x38/0x1e0
stack backtrace:
CPU: 1 PID: 100 Comm: kswapd0 Not tainted 5.9.0-rc3+ #5
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
dump_stack+0x8b/0xb8
check_noncircular+0x12d/0x150
__lock_acquire+0x119c/0x1fc0
lock_acquire+0xa7/0x3d0
? __btrfs_release_delayed_node.part.0+0x3f/0x330
__mutex_lock+0x7e/0x7e0
? __btrfs_release_delayed_node.part.0+0x3f/0x330
? __btrfs_release_delayed_node.part.0+0x3f/0x330
? lock_acquire+0xa7/0x3d0
? find_held_lock+0x2b/0x80
__btrfs_release_delayed_node.part.0+0x3f/0x330
btrfs_evict_inode+0x24c/0x500
evict+0xcf/0x1f0
dispose_list+0x48/0x70
prune_icache_sb+0x44/0x50
super_cache_scan+0x161/0x1e0
do_shrink_slab+0x178/0x3c0
shrink_slab+0x17c/0x290
shrink_node+0x2b2/0x6d0
balance_pgdat+0x30a/0x670
kswapd+0x213/0x4c0
? _raw_spin_unlock_irqrestore+0x41/0x50
? add_wait_queue_exclusive+0x70/0x70
? balance_pgdat+0x670/0x670
kthread+0x138/0x160
? kthread_create_worker_on_cpu+0x40/0x40
ret_from_fork+0x1f/0x30
This happens because when we link in a block group with a new raid index
type we'll create the corresponding sysfs entries for it. This is
problematic because while restriping we're holding the chunk_mutex, and
while mounting we're holding the tree locks.
Fixing this isn't pretty, we move the call to the sysfs stuff into the
btrfs_create_pending_block_groups() work, where we're not holding any
locks. This creates a slight race where other threads could see that
there's no sysfs kobj for that raid type, and race to create the
sysfs dir. Fix this by wrapping the creation in space_info->lock, so we
only get one thread calling kobject_add() for the new directory. We
don't worry about the lock on cleanup as it only gets deleted on
unmount.
On mount it's more straightforward, we loop through the space_infos
already, just check every raid index in each space_info and added the
sysfs entries for the corresponding block groups.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have this thing wrapped in an RCU lock, but it's really not needed.
We create all the space_info's on mount, and we destroy them on unmount.
The list never changes and we're protected from messing with it by the
normal mount/umount path, so kill the RCU stuff around it.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reword and update formats to match variable types.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update formats ]
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
That parameter can easily be derived based on the "data_size" and "nr"
parameters exploit this fact to simply the function's signature. No
functional changes.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The value of this argument can be derived from the total_data as it's
simply the value of the data size + size of btrfs_items being touched.
Move the parameter calculation inside the function. This results in a
simpler interface and also a minor size reduction:
./scripts/bloat-o-meter ctree.original fs/btrfs/ctree.o
add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-34 (-34)
Function old new delta
btrfs_duplicate_item 260 259 -1
setup_items_for_insert 1200 1190 -10
btrfs_insert_empty_items 177 154 -23
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Rearrange statements calculating the offset of the newly added items so
that the calculation has to be done only once. No functional change.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This reports the latest send stream version supported by the kernel as
the feature in /sys/fs/btrfs/features/send_stream_version .
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
send_write_or_clone() basically has an open-coded copy of
btrfs_file_extent_end() except that it (incorrectly) aligns to PAGE_SIZE
instead of sectorsize. Fix and simplify the code by using
btrfs_file_extent_end().
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
send_write() currently copies from the page cache to sctx->read_buf, and
then from sctx->read_buf to sctx->send_buf. Similarly, send_hole()
zeroes sctx->read_buf and then copies from sctx->read_buf to
sctx->send_buf. However, if we write the TLV header manually, we can
copy to sctx->send_buf directly and get rid of sctx->read_buf.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
send_write()/fill_read_buf() have some logic for avoiding reading past
i_size. However, everywhere that we call
send_write()/send_extent_data(), we've already clamped the length down
to i_size. Get rid of the i_size handling, which simplifies the next
change.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that we use the same mechanism to replace all the extents in a file
range with either a hole, an existing extent (when cloning) or a new
extent (when using fallocate), the name of btrfs_insert_clone_extent()
no longer reflects its genericity.
So rename it to btrfs_insert_replace_extent(), since what it does is
to either insert an existing extent or a new extent into a file range.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The function btrfs_punch_hole_range() is now used to replace all the file
extents in a given file range with an extent described in the given struct
btrfs_replace_extent_info argument. This extent can either be an existing
extent that is being cloned or it can be a new extent (namely a prealloc
extent). When that argument is NULL it only punches a hole (drops all the
existing extents) in the file range.
So rename the function to btrfs_replace_file_extents().
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that we can use btrfs_clone_extent_info to convey information for a
new prealloc extent as well, and not just for existing extents that are
being cloned, rename it to btrfs_replace_extent_info, which reflects the
fact that this is now more generic and it is used to replace all existing
extents in a file range with the extent described by the structure.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The value of item_size of struct btrfs_clone_extent_info is always set to
the size of a non-inline file extent item, and in fact the infrastructure
that uses this structure (btrfs_punch_hole_range()) does not work with
inline file extents at all (and it is not supposed to).
So just remove that field from the structure and use directly
sizeof(struct btrfs_file_extent_item) instead. Also assert that the
file extent type is not inline at btrfs_insert_clone_extent().
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When doing an fallocate(), specially a zero range operation, we assume
that reserving 3 units of metadata space is enough, that at most we touch
one leaf in subvolume/fs tree for removing existing file extent items and
inserting a new file extent item. This assumption is generally true for
most common use cases. However when we end up needing to remove file extent
items from multiple leaves, we can end up failing with -ENOSPC and abort
the current transaction, turning the filesystem to RO mode. When this
happens a stack trace like the following is dumped in dmesg/syslog:
[ 1500.620934] ------------[ cut here ]------------
[ 1500.620938] BTRFS: Transaction aborted (error -28)
[ 1500.620973] WARNING: CPU: 2 PID: 30807 at fs/btrfs/inode.c:9724 __btrfs_prealloc_file_range+0x512/0x570 [btrfs]
[ 1500.620974] Modules linked in: btrfs intel_rapl_msr intel_rapl_common kvm_intel (...)
[ 1500.621010] CPU: 2 PID: 30807 Comm: xfs_io Tainted: G W 5.9.0-rc3-btrfs-next-67 #1
[ 1500.621012] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[ 1500.621023] RIP: 0010:__btrfs_prealloc_file_range+0x512/0x570 [btrfs]
[ 1500.621026] Code: 8b 40 50 f0 48 (...)
[ 1500.621028] RSP: 0018:ffffb05fc8803ca0 EFLAGS: 00010286
[ 1500.621030] RAX: 0000000000000000 RBX: ffff9608af276488 RCX: 0000000000000000
[ 1500.621032] RDX: 0000000000000001 RSI: 0000000000000027 RDI: 00000000ffffffff
[ 1500.621033] RBP: ffffb05fc8803d90 R08: 0000000000000001 R09: 0000000000000001
[ 1500.621035] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000003200000
[ 1500.621037] R13: 00000000ffffffe4 R14: ffff9608af275fe8 R15: ffff9608af275f60
[ 1500.621039] FS: 00007fb5b2368ec0(0000) GS:ffff9608b6600000(0000) knlGS:0000000000000000
[ 1500.621041] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1500.621043] CR2: 00007fb5b2366fb8 CR3: 0000000202d38005 CR4: 00000000003706e0
[ 1500.621046] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1500.621047] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 1500.621049] Call Trace:
[ 1500.621076] btrfs_prealloc_file_range+0x10/0x20 [btrfs]
[ 1500.621087] btrfs_fallocate+0xccd/0x1280 [btrfs]
[ 1500.621108] vfs_fallocate+0x14d/0x290
[ 1500.621112] ksys_fallocate+0x3a/0x70
[ 1500.621117] __x64_sys_fallocate+0x1a/0x20
[ 1500.621120] do_syscall_64+0x33/0x80
[ 1500.621123] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 1500.621126] RIP: 0033:0x7fb5b248c477
[ 1500.621128] Code: 89 7c 24 08 (...)
[ 1500.621130] RSP: 002b:00007ffc7bee9060 EFLAGS: 00000293 ORIG_RAX: 000000000000011d
[ 1500.621132] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007fb5b248c477
[ 1500.621134] RDX: 0000000000000000 RSI: 0000000000000010 RDI: 0000000000000003
[ 1500.621136] RBP: 0000557718faafd0 R08: 0000000000000000 R09: 0000000000000000
[ 1500.621137] R10: 0000000003200000 R11: 0000000000000293 R12: 0000000000000010
[ 1500.621139] R13: 0000557718faafb0 R14: 0000557718faa480 R15: 0000000000000003
[ 1500.621151] irq event stamp: 1026217
[ 1500.621154] hardirqs last enabled at (1026223): [<ffffffffba965570>] console_unlock+0x500/0x5c0
[ 1500.621156] hardirqs last disabled at (1026228): [<ffffffffba9654c7>] console_unlock+0x457/0x5c0
[ 1500.621159] softirqs last enabled at (1022486): [<ffffffffbb6003dc>] __do_softirq+0x3dc/0x606
[ 1500.621161] softirqs last disabled at (1022477): [<ffffffffbb4010b2>] asm_call_on_stack+0x12/0x20
[ 1500.621162] ---[ end trace 2955b08408d8b9d4 ]---
[ 1500.621167] BTRFS: error (device sdj) in __btrfs_prealloc_file_range:9724: errno=-28 No space left
When we use fallocate() internally, for reserving an extent for a space
cache, inode cache or relocation, we can't hit this problem since either
there aren't any file extent items to remove from the subvolume tree or
there is at most one.
When using plain fallocate() it's very unlikely, since that would require
having many file extent items representing holes for the target range and
crossing multiple leafs - we attempt to increase the range (merge) of such
file extent items when punching holes, so at most we end up with 2 file
extent items for holes at leaf boundaries.
However when using the zero range operation of fallocate() for a large
range (100+ MiB for example) that's fairly easy to trigger. The following
example reproducer triggers the issue:
$ cat reproducer.sh
#!/bin/bash
umount /dev/sdj &> /dev/null
mkfs.btrfs -f -n 16384 -O ^no-holes /dev/sdj > /dev/null
mount /dev/sdj /mnt/sdj
# Create a 100M file with many file extent items. Punch a hole every 8K
# just to speedup the file creation - we could do 4K sequential writes
# followed by fsync (or O_SYNC) as well, but that takes a lot of time.
file_size=$((100 * 1024 * 1024))
xfs_io -f -c "pwrite -S 0xab -b 10M 0 $file_size" /mnt/sdj/foobar
for ((i = 0; i < $file_size; i += 8192)); do
xfs_io -c "fpunch $i 4096" /mnt/sdj/foobar
done
# Force a transaction commit, so the zero range operation will be forced
# to COW all metadata extents it need to touch.
sync
xfs_io -c "fzero 0 $file_size" /mnt/sdj/foobar
umount /mnt/sdj
$ ./reproducer.sh
wrote 104857600/104857600 bytes at offset 0
100 MiB, 10 ops; 0.0669 sec (1.458 GiB/sec and 149.3117 ops/sec)
fallocate: No space left on device
$ dmesg
<shows the same stack trace pasted before>
To fix this use the existing infrastructure that hole punching and
extent cloning use for replacing a file range with another extent. This
deals with doing the removal of file extent items and inserting the new
one using an incremental approach, reserving more space when needed and
always ensuring we don't leave an implicit hole in the range in case
we need to do multiple iterations and a crash happens between iterations.
A test case for fstests will follow up soon.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It is not used since commit 0096420adb ("btrfs: do not
account global reserve in can_overcommit").
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The function is short and simple, we can get rid of the declaration as
it's not necessary for a static function. Move it before its first
caller. No functional changes.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The function does not have a common exit block and returns immediatelly
so there's no point having the goto. Remove the two cases.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We can check the argument value directly, no need for the temporary
variable.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In the function btrfs_init_dev_replace_tgtdev(), the local variable
devices is used only once, we can remove it.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
On a mounted sprout filesystem, all threads now are using the
sprout::device_list_mutex, and this is the only code using the
seed::device_list_mutex. This patch converts to use the sprouts
fs_info->fs_devices->device_list_mutex.
The same reasoning holds true here, that device delete is holding
the sprout::device_list_mutex.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
On an fs mounted using a sprout device, the seed fs_devices are
maintained in a linked list under fs_info->fs_devices. Each seeds
fs_devices also has device_list_mutex initialized to protect against the
potential race with delete threads. But the delete thread (at
btrfs_rm_device()) is holding the fs_info::fs_devices::device_list_mutex
mutex which belongs to sprout device_list_mutex instead of seed
device_list_mutex. Moreover, there aren't any significient benefits in
using the seed::device_list_mutex instead of sprout::device_list_mutex.
So this patch converts them of using the seed::device_list_mutex to
sprout::device_list_mutex.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
btrfs_sysfs_add_fs_devices() is called by btrfs_sysfs_add_mounted().
btrfs_sysfs_add_mounted() assumes that btrfs_sysfs_add_fs_devices() will
either add sysfs entries for all the devices or none. So this patch keeps up
to its caller expecatation and cleans up the created sysfs entries if it
has to fail at some device in the list.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We don't initialize the sysfs devid kobject and device-link yet for the
seed devices in an sprouted filesystem.
So this patch initializes the seed device devid kobject and the device
link in the sysfs.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Similar to btrfs_sysfs_add_devices_dir()'s refactoring, split
btrfs_sysfs_remove_devices_dir() so that we don't have to use the device
argument to indicate whether to free all devices or just one device.
Export btrfs_sysfs_remove_device() as device operations outside of
sysfs.c now calls this instead of btrfs_sysfs_remove_devices_dir().
btrfs_sysfs_remove_devices_dir() is renamed to
btrfs_sysfs_remove_fs_devices() to suite its new role.
Now, no one outside of sysfs.c calls btrfs_sysfs_remove_fs_devices()
so it is redeclared s static. And the same function had to be moved
before its first caller.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When we add a device we need to add it to sysfs, so instead of using the
btrfs_sysfs_add_devices_dir() fs_devices argument to specify whether to
add a device or all of fs_devices, call the helper function directly
btrfs_sysfs_add_device() and thus make it non-static.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
btrfs_sysfs_remove_devices_dir() return value is unused declare it as
void.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
btrfs_sysfs_remove_devices_dir() removes device link and devid kobject
(sysfs entries) for a device or all the devices in the btrfs_fs_devices.
In preparation to remove these sysfs entries for the seed as well, add
a btrfs_sysfs_remove_device() helper function and avoid code
duplication.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
btrfs_sysfs_add_devices_dir() adds device link and devid kobject
(sysfs entries) for a device or all the devices in the btrfs_fs_devices.
In preparation to add these sysfs entries for the seed as well, add
a btrfs_sysfs_add_device() helper function and avoid code duplication.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If you replace a seed device in a sprouted fs, it appears to have
successfully replaced the seed device, but if you look closely, it
didn't. Here is an example.
$ mkfs.btrfs /dev/sda
$ btrfstune -S1 /dev/sda
$ mount /dev/sda /btrfs
$ btrfs device add /dev/sdb /btrfs
$ umount /btrfs
$ btrfs device scan --forget
$ mount -o device=/dev/sda /dev/sdb /btrfs
$ btrfs replace start -f /dev/sda /dev/sdc /btrfs
$ echo $?
0
BTRFS info (device sdb): dev_replace from /dev/sda (devid 1) to /dev/sdc started
BTRFS info (device sdb): dev_replace from /dev/sda (devid 1) to /dev/sdc finished
$ btrfs fi show
Label: none uuid: ab2c88b7-be81-4a7e-9849-c3666e7f9f4f
Total devices 2 FS bytes used 256.00KiB
devid 1 size 3.00GiB used 520.00MiB path /dev/sdc
devid 2 size 3.00GiB used 896.00MiB path /dev/sdb
Label: none uuid: 10bd3202-0415-43af-96a8-d5409f310a7e
Total devices 1 FS bytes used 128.00KiB
devid 1 size 3.00GiB used 536.00MiB path /dev/sda
So as per the replace start command and kernel log replace was successful.
Now let's try to clean mount.
$ umount /btrfs
$ btrfs device scan --forget
$ mount -o device=/dev/sdc /dev/sdb /btrfs
mount: /btrfs: wrong fs type, bad option, bad superblock on /dev/sdb, missing codepage or helper program, or other error.
[ 636.157517] BTRFS error (device sdc): failed to read chunk tree: -2
[ 636.180177] BTRFS error (device sdc): open_ctree failed
That's because per dev items it is still looking for the original seed
device.
$ btrfs inspect-internal dump-tree -d /dev/sdb
item 0 key (DEV_ITEMS DEV_ITEM 1) itemoff 16185 itemsize 98
devid 1 total_bytes 3221225472 bytes_used 545259520
io_align 4096 io_width 4096 sector_size 4096 type 0
generation 6 start_offset 0 dev_group 0
seek_speed 0 bandwidth 0
uuid 59368f50-9af2-4b17-91da-8a783cc418d4 <--- seed uuid
fsid 10bd3202-0415-43af-96a8-d5409f310a7e <--- seed fsid
item 1 key (DEV_ITEMS DEV_ITEM 2) itemoff 16087 itemsize 98
devid 2 total_bytes 3221225472 bytes_used 939524096
io_align 4096 io_width 4096 sector_size 4096 type 0
generation 0 start_offset 0 dev_group 0
seek_speed 0 bandwidth 0
uuid 56a0a6bc-4630-4998-8daf-3c3030c4256a <- sprout uuid
fsid ab2c88b7-be81-4a7e-9849-c3666e7f9f4f <- sprout fsid
But the replaced target has the following uuid+fsid in its superblock
which doesn't match with the expected uuid+fsid in its devitem.
$ btrfs in dump-super /dev/sdc | egrep '^generation|dev_item.uuid|dev_item.fsid|devid'
generation 20
dev_item.uuid 59368f50-9af2-4b17-91da-8a783cc418d4
dev_item.fsid ab2c88b7-be81-4a7e-9849-c3666e7f9f4f [match]
dev_item.devid 1
So if you provide the original seed device the mount shall be
successful. Which so long happening in the test case btrfs/163.
$ btrfs device scan --forget
$ mount -o device=/dev/sda /dev/sdb /btrfs
Fix in this patch:
If a seed is not sprouted then there is no replacement of it, because of
its read-only filesystem with a read-only device. Similarly, in the case
of a sprouted filesystem, the seed device is still read only. So, mark
it as you can't replace a seed device, you can only add a new device and
then delete the seed device. If replace is attempted then returns
-EINVAL.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Systems booting without the initramfs seems to scan an unusual kind
of device path (/dev/root). And at a later time, the device is updated
to the correct path. We generally print the process name and PID of the
process scanning the device but we don't capture the same information if
the device path is rescanned with a different pathname.
The current message is too long, so drop the unnecessary UUID and add
process name and PID.
While at this also update the duplicate device warning to include the
process name and PID so the messages are consistent
CC: stable@vger.kernel.org # 4.19+
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=89721
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
I'm a actual human being so am incapable of converting u64 to s64 in my
head, so add a helper to get the pretty name of a root objectid and use
that helper to spit out the name for any special roots for leaked roots,
so I don't have to scratch my head and figure out which root I messed up
the refs for.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
/sys/fs/<fsid>/exclusive_operation contains the currently executing
exclusive operation. Add a sysfs_notify() when operation end, so
userspace can be notified of exclusive operation is finished.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Instead of using a flag bit for exclusive operation, use a variable to
store which exclusive operation is being performed. Introduce an API
to start and finish an exclusive operation.
This would enable another way for tools to check which operation is
running on why starting an exclusive operation failed. The followup
patch adds a sysfs_notify() to alert userspace when the state changes, so
userspace can perform select() on it to get notified of the change.
This would enable us to enqueue a command which will wait for current
exclusive operation to complete before issuing the next exclusive
operation. This has been done synchronously as opposed to a background
process, or else error collection (if any) will become difficult.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update comments ]
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It's counterintuitive to have a function named btrfs_inode_xxx which
takes a generic inode. Also move the function to btrfs_inode.h so that
it has access to the definition of struct btrfs_inode.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
I've made this change separate since it requires both of the newly added
NESTED flags and I didn't want to slip it into one of those changes.
If we do a double split of a node we can end up doing a
BTRFS_NESTED_SPLIT on level 0, which throws lockdep off because it
appears as a double lock. Since we're maxed out on subclasses, use
BTRFS_NESTED_NEW_ROOT if we had to do a double split. This is OK
because we won't have to do a double split if we had to insert a new
root, and the new root would be at a higher level anyway.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The way we add new roots is confusing from a locking perspective for
lockdep. We generally have the rule that we lock things in order from
highest level to lowest, but in the case of adding a new level to the
tree we actually allocate a new block for the root, which makes the
locking go in reverse. A similar issue exists for snapshotting, we cow
the original root for the root of a new tree, however they're at the
same level. Address this by using BTRFS_NESTING_NEW_ROOT for these
operations.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If we are splitting a leaf/node, we could do something like the
following
lock(leaf) BTRFS_NESTING_NORMAL
lock(left) BTRFS_NESTING_LEFT + BTRFS_NESTING_COW
push from leaf -> left
reset path to point to left
split left
allocate new block, lock block BTRFS_NESTING_SPLIT
at the new block point we need to have a different nesting level,
because we have already used either BTRFS_NESTING_LEFT or
BTRFS_NESTING_RIGHT when pushing items from the original leaf into the
adjacent leaves.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
For similar reasons as BTRFS_NESTING_COW, we need
BTRFS_NESTING_LEFT/RIGHT_COW. The pattern is this
lock leaf -> BTRFS_NESTING_NORMAL
cow leaf -> BTRFS_NESTING_COW
split leaf
lock left -> BTRFS_NESTING_LEFT
cow left -> BTRFS_NESTING_LEFT_COW
We need this in order to indicate to lockdep that these locks are
discrete and are being taken in a safe order.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Our lockdep maps are based on rootid+level, however in some cases we
will lock adjacent blocks on the same level, namely in searching forward
or in split/balance. Because of this lockdep will complain, so we need
a separate subclass to indicate to lockdep that these are different
locks.
lock leaf -> BTRFS_NESTING_NORMAL
cow leaf -> BTRFS_NESTING_COW
split leaf
lock left -> BTRFS_NESTING_LEFT
lock right -> BTRFS_NESTING_RIGHT
The above graph illustrates the need for this new nesting subclass.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When we COW a block we are holding a lock on the original block, and
then we lock the new COW block. Because our lockdep maps are based on
root + level, this will make lockdep complain. We need a way to
indicate a subclass for locking the COW'ed block, so plumb through our
btrfs_lock_nesting from btrfs_cow_block down to the btrfs_init_buffer,
and then introduce BTRFS_NESTING_COW to be used for cow'ing blocks.
The reason I've added all this extra infrastructure is because there
will be need of different nesting classes in follow up patches.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We will need these when we switch to an rwsem, so plumb in the
infrastructure here to use later on. I violate the 80 character limit
some here because it'll be cleaned up later.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Our current tree locking stuff allows us to recurse with read locks if
we're already holding the write lock. This is necessary for the space
cache inode, as we could be holding a lock on the root_tree root when we
need to cache a block group, and thus need to be able to read down the
root_tree to read in the inode cache.
We can get away with this in our current locking, but we won't be able
to with a rwsem. Handle this by purposefully annotating the places
where we require recursion, so that in the future we can maybe come up
with a way to avoid the recursion. In the case of the free space inode,
this will be superseded by the free space tree.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Nested locking with lockdep and everything else refers to lock hierarchy
within the same lock map. This is how we indicate the same locks for
different objects are ok to take in a specific order, for our use case
that would be to take the lock on a leaf and then take a lock on an
adjacent leaf.
What ->lock_nested _actually_ refers to is if we happen to already be
holding the write lock on the extent buffer and we're allowing a read
lock to be taken on that extent buffer, which is recursion. Rename this
so we don't get confused when we switch to a rwsem and have to start
using the _nested helpers.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Instead of opencoding filemap_write_and_wait simply call syncblockdev as
it makes it abundantly clear what's going on and why this is used. No
semantics changes.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Following the refactor of btrfs_free_stale_devices in
7bcb8164ad ("btrfs: use device_list_mutex when removing stale devices")
fs_devices are freed after they have been iterated by the inner
list_for_each so the use-after-free fixed by introducing the break in
fd649f10c3 ("btrfs: Fix use-after-free when cleaning up fs_devs with
a single stale device") is no longer necessary. Just remove it
altogether. No functional changes.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Invert unlocked to locked and exploit the fact it can only ever be
modified if we are adding a new device to a seed filesystem. This allows
to simplify the check in error: label. No semantics changes.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When adding a new device there's a mandatory check to see if a device is
being duplicated to the filesystem it's added to. Since this is a
read-only operations not necessary to take device_list_mutex and can simply
make do with an rcu-readlock.
Using just RCU is safe because there won't be another device add delete
running in parallel as btrfs_init_new_device is called only from
btrfs_ioctl_add_dev.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
[BUG]
With a crafted image, btrfs can panic at btrfs_del_csums():
kernel BUG at fs/btrfs/ctree.c:3188!
invalid opcode: 0000 [#1] SMP PTI
CPU: 0 PID: 1156 Comm: btrfs-transacti Not tainted 5.0.0-rc8+ #9
RIP: 0010:btrfs_set_item_key_safe+0x16c/0x180
RSP: 0018:ffff976141257ab8 EFLAGS: 00010202
RAX: 0000000000000001 RBX: ffff898a6b890930 RCX: 0000000004b70000
RDX: 0000000000000000 RSI: ffff976141257bae RDI: ffff976141257acf
RBP: ffff976141257b10 R08: 0000000000001000 R09: ffff9761412579a8
R10: 0000000000000000 R11: 0000000000000000 R12: ffff976141257abe
R13: 0000000000000003 R14: ffff898a6a8be578 R15: ffff976141257bae
FS: 0000000000000000(0000) GS:ffff898a77a00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f779d9cd624 CR3: 000000022b2b4006 CR4: 00000000000206f0
Call Trace:
truncate_one_csum+0xac/0xf0
btrfs_del_csums+0x24f/0x3a0
__btrfs_free_extent.isra.72+0x5a7/0xbe0
__btrfs_run_delayed_refs+0x539/0x1120
btrfs_run_delayed_refs+0xdb/0x1b0
btrfs_commit_transaction+0x52/0x950
? start_transaction+0x94/0x450
transaction_kthread+0x163/0x190
kthread+0x105/0x140
? btrfs_cleanup_transaction+0x560/0x560
? kthread_destroy_worker+0x50/0x50
ret_from_fork+0x35/0x40
Modules linked in:
---[ end trace 93bf9db00e6c374e ]---
[CAUSE]
This crafted image has a tricky key order corruption:
checksum tree key (CSUM_TREE ROOT_ITEM 0)
node 29741056 level 1 items 14 free 107 generation 19 owner CSUM_TREE
...
key (EXTENT_CSUM EXTENT_CSUM 73785344) block 29757440 gen 19
key (EXTENT_CSUM EXTENT_CSUM 77594624) block 29753344 gen 19
...
leaf 29757440 items 5 free space 150 generation 19 owner CSUM_TREE
item 0 key (EXTENT_CSUM EXTENT_CSUM 73785344) itemoff 2323 itemsize 1672
range start 73785344 end 75497472 length 1712128
item 1 key (EXTENT_CSUM EXTENT_CSUM 75497472) itemoff 2319 itemsize 4
range start 75497472 end 75501568 length 4096
item 2 key (EXTENT_CSUM EXTENT_CSUM 75501568) itemoff 579 itemsize 1740
range start 75501568 end 77283328 length 1781760
item 3 key (EXTENT_CSUM EXTENT_CSUM 77283328) itemoff 575 itemsize 4
range start 77283328 end 77287424 length 4096
item 4 key (EXTENT_CSUM EXTENT_CSUM 4120596480) itemoff 275 itemsize 300 <<<
range start 4120596480 end 4120903680 length 307200
leaf 29753344 items 3 free space 1936 generation 19 owner CSUM_TREE
item 0 key (18446744073457893366 EXTENT_CSUM 77594624) itemoff 2323 itemsize 1672
range start 77594624 end 79306752 length 1712128
...
Note the item 4 key of leaf 29757440, which is obviously too large, and
even larger than the first key of the next leaf.
However it still follows the key order in that tree block, thus tree
checker is unable to detect it at read time, since tree checker can only
work inside one leaf, thus such complex corruption can't be detected in
advance.
[FIX]
The next time to detect such problem is at tree block merge time,
which is in push_node_left(), balance_node_right(), push_leaf_left() or
push_leaf_right().
Now we check if the key order of the right-most key of the left node is
larger than the left-most key of the right node.
By this we don't need to call the full tree-checker, while still keeping
the key order correct as key order in each node is already checked by
tree checker thus we only need to check the above two slots.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202833
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
[BUG]
With a crafted image, btrfs can panic at insert_inline_extent_backref():
kernel BUG at fs/btrfs/extent-tree.c:1857!
invalid opcode: 0000 [#1] SMP PTI
CPU: 0 PID: 1117 Comm: btrfs-transacti Not tainted 5.0.0-rc8+ #9
RIP: 0010:insert_inline_extent_backref+0xcc/0xe0
RSP: 0018:ffffac4dc1287be8 EFLAGS: 00010293
RAX: 0000000000000000 RBX: 0000000000000007 RCX: 0000000000000001
RDX: 0000000000001000 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffffac4dc1287c28 R08: ffffac4dc1287ab8 R09: ffffac4dc1287ac0
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: ffff8febef88a540 R14: ffff8febeaa7bc30 R15: 0000000000000000
FS: 0000000000000000(0000) GS:ffff8febf7a00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f663ace94c0 CR3: 0000000235698006 CR4: 00000000000206f0
Call Trace:
? _cond_resched+0x1a/0x50
__btrfs_inc_extent_ref.isra.64+0x7e/0x240
? btrfs_merge_delayed_refs+0xa5/0x330
__btrfs_run_delayed_refs+0x653/0x1120
btrfs_run_delayed_refs+0xdb/0x1b0
btrfs_commit_transaction+0x52/0x950
? start_transaction+0x94/0x450
transaction_kthread+0x163/0x190
kthread+0x105/0x140
? btrfs_cleanup_transaction+0x560/0x560
? kthread_destroy_worker+0x50/0x50
ret_from_fork+0x35/0x40
Modules linked in:
---[ end trace 2ad8b3de903cf825 ]---
[CAUSE]
Due to extent tree corruption (still valid by itself, but bad cross
ref), we can allocate an extent which is still in extent tree. The
offending tree block of that case is from csum tree. The newly
allocated tree block is also for csum tree.
Then we will try to insert a tree block ref for the existing tree block
ref.
For a tree extent item, tree block can never be shared directly by the
same tree twice. We have such BUG_ON() to prevent such problem, but
this is not a proper error handling.
[FIX]
Replace that BUG_ON() with proper error message and leaf dump for debug
build.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202829
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
__btrfs_free_extent() is doing two things:
1. Reduce the refs number of an extent backref
Either it's an inline extent backref (inside EXTENT/METADATA item) or
a keyed extent backref (SHARED_* item).
We only need to locate that backref line, either reduce the number or
remove the backref line completely.
2. Update the refs count in EXTENT/METADATA_ITEM
During step 1), we will try to locate the EXTENT/METADATA_ITEM without
triggering another btrfs_search_slot() as fast path.
Only when we fail to locate that item, we will trigger another
btrfs_search_slot() to get that EXTENT/METADATA_ITEM after we
updated/deleted the backref line.
And we have a lot of strict checks on things like refs_to_drop against
extent refs and special case checks for single ref extents.
There are 7 BUG_ON()s, although they're doing correct checks, they can
be triggered by crafted images.
This patch improves the function:
- Introduce two examples to show what __btrfs_free_extent() is doing
One inline backref case and one keyed case. Should cover most cases.
- Kill all BUG_ON()s with proper error message and optional leaf dump
- Add comment to show the overall flow
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202819
[ The report triggers one BUG_ON() in __btrfs_free_extent() ]
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Although we have start, len check for extent buffer reader/write (e.g.
read_extent_buffer()), these checks have limitations:
- No overflow check
Values like start = 1024 len = -1024 can still pass the basic
(start + len) > eb->len check.
- Checks are not consistent
For read_extent_buffer() we only check (start + len) against eb->len.
While for memcmp_extent_buffer() we also check start against eb->len.
- Different error reporting mechanism
We use WARN() in read_extent_buffer() but BUG() in
memcpy_extent_buffer().
- Still modify memory if the request is obviously wrong
In read_extent_buffer() even we find (start + len) > eb->len, we still
call memset(dst, 0, len), which can easily cause memory access error
if start + len overflows.
To address above problems, this patch creates a new common function to
check such access, check_eb_range().
- Add overflow check
This function checks start, start + len against eb->len and overflow
check.
- Unified checks
- Unified error reports
Will call WARN() if CONFIG_BTRFS_DEBUG is configured.
And also do btrfs_warn() message for non-debug build.
- Exit ASAP if check fails
No more possible memory corruption.
- Add extra comment for @start @len used in those functions as it's
sometimes confused with the logical addressing instead of a range
inside the eb space
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202817
[ Inspired by above report, the report itself is already addressed ]
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ use check_add_overflow ]
Signed-off-by: David Sterba <dsterba@suse.com>
To avoid duplicating 3 lines of code the error detection logic in
init_tree_roots is somewhat quirky. It first checks for the presence of
any error condition, then checks for the specific condition to perform
any specific actions. That's spurious because directly checking for
each respective error condition and doing the necessary steps is more
obvious. While at it change the -EUCLEAN to -EIO in case the extent
buffer is not read correctly, this is in line with other sites which
return -EIO when the eb couldn't be read.
Additionally it results in smaller code and the code reads
more linearly:
add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-95 (-95)
Function old new delta
open_ctree 17243 17148 -95
Total: Before=113104, After=113009, chg -0.08%
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
[BUG]
When quota is enabled for TEST_DEV, generic/013 sometimes fails like this:
generic/013 14s ... _check_dmesg: something found in dmesg (see xfstests-dev/results//generic/013.dmesg)
And with the following metadata leak:
BTRFS warning (device dm-3): qgroup 0/1370 has unreleased space, type 2 rsv 49152
------------[ cut here ]------------
WARNING: CPU: 2 PID: 47912 at fs/btrfs/disk-io.c:4078 close_ctree+0x1dc/0x323 [btrfs]
Call Trace:
btrfs_put_super+0x15/0x17 [btrfs]
generic_shutdown_super+0x72/0x110
kill_anon_super+0x18/0x30
btrfs_kill_super+0x17/0x30 [btrfs]
deactivate_locked_super+0x3b/0xa0
deactivate_super+0x40/0x50
cleanup_mnt+0x135/0x190
__cleanup_mnt+0x12/0x20
task_work_run+0x64/0xb0
__prepare_exit_to_usermode+0x1bc/0x1c0
__syscall_return_slowpath+0x47/0x230
do_syscall_64+0x64/0xb0
entry_SYSCALL_64_after_hwframe+0x44/0xa9
---[ end trace a6cfd45ba80e4e06 ]---
BTRFS error (device dm-3): qgroup reserved space leaked
BTRFS info (device dm-3): disk space caching is enabled
BTRFS info (device dm-3): has skinny extents
[CAUSE]
The qgroup preallocated meta rsv operations of that offending root are:
btrfs_delayed_inode_reserve_metadata: rsv_meta_prealloc root=1370 num_bytes=131072
btrfs_delayed_inode_reserve_metadata: rsv_meta_prealloc root=1370 num_bytes=131072
btrfs_subvolume_reserve_metadata: rsv_meta_prealloc root=1370 num_bytes=49152
btrfs_delayed_inode_release_metadata: convert_meta_prealloc root=1370 num_bytes=-131072
btrfs_delayed_inode_release_metadata: convert_meta_prealloc root=1370 num_bytes=-131072
It's pretty obvious that, we reserve qgroup meta rsv in
btrfs_subvolume_reserve_metadata(), but doesn't have corresponding
release/convert calls in btrfs_subvolume_release_metadata().
This leads to the leakage.
[FIX]
To fix this bug, we should follow what we're doing in
btrfs_delalloc_reserve_metadata(), where we reserve qgroup space, and
add it to block_rsv->qgroup_rsv_reserved.
And free the qgroup reserved metadata space when releasing the
block_rsv.
To do this, we need to change the btrfs_subvolume_release_metadata() to
accept btrfs_root, and record the qgroup_to_release number, and call
btrfs_qgroup_convert_reserved_meta() for it.
Fixes: 733e03a0b2 ("btrfs: qgroup: Split meta rsv type into meta_prealloc and meta_pertrans")
CC: stable@vger.kernel.org # 4.19+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
For delayed inode facility, qgroup metadata is reserved for it, and
later freed.
However we're freeing more bytes than we reserved.
In btrfs_delayed_inode_reserve_metadata():
num_bytes = btrfs_calc_metadata_size(fs_info, 1);
...
ret = btrfs_qgroup_reserve_meta_prealloc(root,
fs_info->nodesize, true);
...
if (!ret) {
node->bytes_reserved = num_bytes;
But in btrfs_delayed_inode_release_metadata():
if (qgroup_free)
btrfs_qgroup_free_meta_prealloc(node->root,
node->bytes_reserved);
else
btrfs_qgroup_convert_reserved_meta(node->root,
node->bytes_reserved);
This means, we're always releasing more qgroup metadata rsv than we have
reserved.
This won't trigger selftest warning, as btrfs qgroup metadata rsv has
extra protection against cases like quota enabled half-way.
But we still need to fix this problem any way.
This patch will use the same num_bytes for qgroup metadata rsv so we
could handle it correctly.
Fixes: f218ea6c47 ("btrfs: delayed-inode: Remove wrong qgroup meta reservation calls")
CC: stable@vger.kernel.org # 4.19+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When closing and freeing the source device we could end up doing our
final blkdev_put() on the bdev, which will grab the bd_mutex. As such
we want to be holding as few locks as possible, so move this call
outside of the dev_replace->lock_finishing_cancel_unmount lock. Since
we're modifying the fs_devices we need to make sure we're holding the
uuid_mutex here, so take that as well.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
btrfs_prepare_sprout is called when the first rw device is added to a
seed filesystem. This means the filesystem can't have its alloc_list
be non-empty, since seed filesystems are read only. Simply remove the
code altogether.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Without good understanding of how seed devices works it's hard to grok
some of what the code in open_seed_devices or btrfs_prepare_sprout does.
Add comments hopefully reducing some of the cognitive load.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
While this patch touches a bunch of files the conversion is
straighforward. Instead of using the implicit linked list anchored at
btrfs_fs_devices::seed the code is switched to using
list_for_each_entry.
Previous patches in the series already factored out code that processed
both main and seed devices so in those cases the factored out functions
are called on the main fs_devices and then on every seed dev inside
list_for_each_entry.
Using list api also allows to simplify deletion from the seed dev list
performed in btrfs_rm_device and btrfs_rm_dev_replace_free_srcdev by
substituting a while() loop with a simple list_del_init.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It makes no sense to have sysfs-related routines be responsible for
properly initialising the fs_info pointer of struct btrfs_fs_device.
Instead this can be streamlined by making it the responsibility of
btrfs_init_devices_late to initialize it. That function already
initializes fs_info of every individual device in btrfs_fs_devices.
As far as clearing it is concerned it makes sense to move it to
close_fs_devices. That function is only called when struct
btrfs_fs_devices is no longer in use - either for holding seeds or
main devices for a mounted filesystem.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The return value of this function conveys absolutely no information.
All callers already check the state of fs_devices->opened to decide how
to proceed. So convert the function to returning void. While at it make
btrfs_close_devices also return void.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This prepares the code to switching seeds devices to a proper list.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This is in preparation for moving fs_devices to proper lists.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There's no practical reason too use 'err' as a variable to convey
errors. In fact it's value is either set explicitly in the beginning of
the function or it simply takes the value of 'ret'. Not conforming to
the usual pattern of having ret be the only variable used to convey
errors makes the code more error prone to bugs. In fact one such bug
was introduced by 6bf9e4bd6a ("btrfs: inode: Verify inode mode toi
avoid NULL pointer dereference") by assigning the error value to 'ret'
and not 'err'.
Let's fix that issue and make the function less tricky by leaving only
ret to convey error values.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
iomap dio will run generic_write_sync() for us if the iocb is DSYNC.
This is problematic for us because of 2 reasons:
1. we hold the inode_lock() during this operation, and we take it in
generic_write_sync()
2. we hold a read lock on the dio_sem but take the write lock in fsync
Since we don't want to rip out this code right now, but reworking the
locking is a bit much to do at this point, work around this problem with
this masterpiece of a patch.
First, we clear DSYNC on the iocb so that the iomap stuff doesn't know
that it needs to handle the sync. We save this fact in
current->journal_info, because we need to see do special things once
we're in iomap_begin, and we have no way to pass private information
into iomap_dio_rw().
Next we specify a separate iomap_dio_ops for sync, which implements an
->end_io() callback that gets called when the dio completes. This is
important for AIO, because we really do need to run generic_write_sync()
if we complete asynchronously. However if we're still in the submitting
context when we enter ->end_io() we clear the flag so that the submitter
knows they're the ones that needs to run generic_write_sync().
This is meant to be temporary. We need to work out how to eliminate the
inode_lock() and the dio_sem in our fsync and use another mechanism to
protect these operations.
Tested-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We're using direct io implementation based on buffer heads. This patch
switches to the new iomap infrastructure.
Switch from __blockdev_direct_IO() to iomap_dio_rw(). Rename
btrfs_get_blocks_direct() to btrfs_dio_iomap_begin() and use it as
iomap_begin() for iomap direct I/O functions. This function allocates
and locks all the blocks required for the I/O. btrfs_submit_direct() is
used as the submit_io() hook for direct I/O ops.
Since we need direct I/O reads to go through iomap_dio_rw(), we change
file_operations.read_iter() to a btrfs_file_read_iter() which calls
btrfs_direct_IO() for direct reads and falls back to
generic_file_buffered_read() for incomplete reads and buffered reads.
We don't need address_space.direct_IO() anymore: set it to noop.
Similarly, we don't need flags used in __blockdev_direct_IO(). iomap is
capable of direct I/O reads from a hole, so we don't need to return
-ENOENT.
Btrfs direct I/O is now done under i_rwsem, shared in case of reads and
exclusive in case of writes. This guards against simultaneous truncates.
Use iomap->iomap_end() to check for failed or incomplete direct I/O:
- for writes, call __endio_write_update_ordered()
- for reads, unlock extents
btrfs_dio_data is now hooked in iomap->private and not
current->journal_info. It carries the reservation variable and the
amount of data submitted, so we can calculate the amount of data to call
__endio_write_update_ordered in case of an error.
This patch removes last use of struct buffer_head from btrfs.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Commit 1c11b63eff ("btrfs: replace pending/pinned chunks lists with io
tree") introduced btrfs_device::alloc_state extent io tree, but it
doesn't initialize the fs_info and owner member.
This means the following features are not properly supported:
- Fs owner report for insert_state() error
Without fs_info initialized, although btrfs_err() won't panic, it
won't output which fs is causing the error.
- Wrong owner for trace events
alloc_state will get the owner as pinned extents.
Fix this by assiging proper fs_info and owner for
btrfs_device::alloc_state.
Fixes: 1c11b63eff ("btrfs: replace pending/pinned chunks lists with io tree")
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Since it's inclusion on 9afc66498a ("btrfs: block-group: refactor how
we read one block group item") this function always returned 0, so there
is no need to check for the returned value.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Marcos Paulo de Souza <mpdesouza@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The compilation with W=1 generates the following warnings:
fs/btrfs/sysfs.c:1630:6: warning: variable 'ret' set but not used [-Wunused-but-set-variable]
1630 | int ret;
| ^~~
fs/btrfs/sysfs.c:1629:6: warning: variable 'features' set but not used [-Wunused-but-set-variable]
1629 | u64 features;
| ^~~~~~~~
[ The unused variables are leftover from e410e34fad ("Revert "btrfs:
synchronize incompat feature bits with sysfs files""), which needs
to be properly fixed by moving feature bit manipulation from the sysfs
context. Silence the warning to save pepople time, we got several
reports. ]
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Currently regardless of a full or a fast fsync we always wait for ordered
extents to complete, and then start logging the inode after that. However
for fast fsyncs we can just wait for the writeback to complete, we don't
need to wait for the ordered extents to complete since we use the list of
modified extents maps to figure out which extents we must log and we can
get their checksums directly from the ordered extents that are still in
flight, otherwise look them up from the checksums tree.
Until commit b5e6c3e170 ("btrfs: always wait on ordered extents at
fsync time"), for fast fsyncs, we used to start logging without even
waiting for the writeback to complete first, we would wait for it to
complete after logging, while holding a transaction open, which lead to
performance issues when using cgroups and probably for other cases too,
as wait for IO while holding a transaction handle should be avoided as
much as possible. After that, for fast fsyncs, we started to wait for
ordered extents to complete before starting to log, which adds some
latency to fsyncs and we even got at least one report about a performance
drop which bisected to that particular change:
https://lore.kernel.org/linux-btrfs/20181109215148.GF23260@techsingularity.net/
This change makes fast fsyncs only wait for writeback to finish before
starting to log the inode, instead of waiting for both the writeback to
finish and for the ordered extents to complete. This brings back part of
the logic we had that extracts checksums from in flight ordered extents,
which are not yet in the checksums tree, and making sure transaction
commits wait for the completion of ordered extents previously logged
(by far most of the time they have already completed by the time a
transaction commit starts, resulting in no wait at all), to avoid any
data loss if an ordered extent completes after the transaction used to
log an inode is committed, followed by a power failure.
When there are no other tasks accessing the checksums and the subvolume
btrees, the ordered extent completion is pretty fast, typically taking
100 to 200 microseconds only in my observations. However when there are
other tasks accessing these btrees, ordered extent completion can take a
lot more time due to lock contention on nodes and leaves of these btrees.
I've seen cases over 2 milliseconds, which starts to be significant. In
particular when we do have concurrent fsyncs against different files there
is a lot of contention on the checksums btree, since we have many tasks
writing the checksums into the btree and other tasks that already started
the logging phase are doing lookups for checksums in the btree.
This change also turns all ranged fsyncs into full ranged fsyncs, which
is something we already did when not using the NO_HOLES features or when
doing a full fsync. This is to guarantee we never miss checksums due to
writeback having been triggered only for a part of an extent, and we end
up logging the full extent but only checksums for the written range, which
results in missing checksums after log replay. Allowing ranged fsyncs to
operate again only in the original range, when using the NO_HOLES feature
and doing a fast fsync is doable but requires some non trivial changes to
the writeback path, which can always be worked on later if needed, but I
don't think they are a very common use case.
Several tests were performed using fio for different numbers of concurrent
jobs, each writing and fsyncing its own file, for both sequential and
random file writes. The tests were run on bare metal, no virtualization,
on a box with 12 cores (Intel i7-8700), 64Gb of RAM and a NVMe device,
with a kernel configuration that is the default of typical distributions
(debian in this case), without debug options enabled (kasan, kmemleak,
slub debug, debug of page allocations, lock debugging, etc).
The following script that calls fio was used:
$ cat test-fsync.sh
#!/bin/bash
DEV=/dev/nvme0n1
MNT=/mnt/btrfs
MOUNT_OPTIONS="-o ssd -o space_cache=v2"
MKFS_OPTIONS="-d single -m single"
if [ $# -ne 5 ]; then
echo "Use $0 NUM_JOBS FILE_SIZE FSYNC_FREQ BLOCK_SIZE [write|randwrite]"
exit 1
fi
NUM_JOBS=$1
FILE_SIZE=$2
FSYNC_FREQ=$3
BLOCK_SIZE=$4
WRITE_MODE=$5
if [ "$WRITE_MODE" != "write" ] && [ "$WRITE_MODE" != "randwrite" ]; then
echo "Invalid WRITE_MODE, must be 'write' or 'randwrite'"
exit 1
fi
cat <<EOF > /tmp/fio-job.ini
[writers]
rw=$WRITE_MODE
fsync=$FSYNC_FREQ
fallocate=none
group_reporting=1
direct=0
bs=$BLOCK_SIZE
ioengine=sync
size=$FILE_SIZE
directory=$MNT
numjobs=$NUM_JOBS
EOF
echo "performance" | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
echo
echo "Using config:"
echo
cat /tmp/fio-job.ini
echo
umount $MNT &> /dev/null
mkfs.btrfs -f $MKFS_OPTIONS $DEV
mount $MOUNT_OPTIONS $DEV $MNT
fio /tmp/fio-job.ini
umount $MNT
The results were the following:
*************************
*** sequential writes ***
*************************
==== 1 job, 8GiB file, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=36.6MiB/s (38.4MB/s), 36.6MiB/s-36.6MiB/s (38.4MB/s-38.4MB/s), io=8192MiB (8590MB), run=223689-223689msec
After patch:
WRITE: bw=40.2MiB/s (42.1MB/s), 40.2MiB/s-40.2MiB/s (42.1MB/s-42.1MB/s), io=8192MiB (8590MB), run=203980-203980msec
(+9.8%, -8.8% runtime)
==== 2 jobs, 4GiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=35.8MiB/s (37.5MB/s), 35.8MiB/s-35.8MiB/s (37.5MB/s-37.5MB/s), io=8192MiB (8590MB), run=228950-228950msec
After patch:
WRITE: bw=43.5MiB/s (45.6MB/s), 43.5MiB/s-43.5MiB/s (45.6MB/s-45.6MB/s), io=8192MiB (8590MB), run=188272-188272msec
(+21.5% throughput, -17.8% runtime)
==== 4 jobs, 2GiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=50.1MiB/s (52.6MB/s), 50.1MiB/s-50.1MiB/s (52.6MB/s-52.6MB/s), io=8192MiB (8590MB), run=163446-163446msec
After patch:
WRITE: bw=64.5MiB/s (67.6MB/s), 64.5MiB/s-64.5MiB/s (67.6MB/s-67.6MB/s), io=8192MiB (8590MB), run=126987-126987msec
(+28.7% throughput, -22.3% runtime)
==== 8 jobs, 1GiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=64.0MiB/s (68.1MB/s), 64.0MiB/s-64.0MiB/s (68.1MB/s-68.1MB/s), io=8192MiB (8590MB), run=126075-126075msec
After patch:
WRITE: bw=86.8MiB/s (91.0MB/s), 86.8MiB/s-86.8MiB/s (91.0MB/s-91.0MB/s), io=8192MiB (8590MB), run=94358-94358msec
(+35.6% throughput, -25.2% runtime)
==== 16 jobs, 512MiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=79.8MiB/s (83.6MB/s), 79.8MiB/s-79.8MiB/s (83.6MB/s-83.6MB/s), io=8192MiB (8590MB), run=102694-102694msec
After patch:
WRITE: bw=107MiB/s (112MB/s), 107MiB/s-107MiB/s (112MB/s-112MB/s), io=8192MiB (8590MB), run=76446-76446msec
(+34.1% throughput, -25.6% runtime)
==== 32 jobs, 512MiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=93.2MiB/s (97.7MB/s), 93.2MiB/s-93.2MiB/s (97.7MB/s-97.7MB/s), io=16.0GiB (17.2GB), run=175836-175836msec
After patch:
WRITE: bw=111MiB/s (117MB/s), 111MiB/s-111MiB/s (117MB/s-117MB/s), io=16.0GiB (17.2GB), run=147001-147001msec
(+19.1% throughput, -16.4% runtime)
==== 64 jobs, 512MiB files, fsync frequency 1, block size 64KiB ====
Before patch:
WRITE: bw=108MiB/s (114MB/s), 108MiB/s-108MiB/s (114MB/s-114MB/s), io=32.0GiB (34.4GB), run=302656-302656msec
After patch:
WRITE: bw=133MiB/s (140MB/s), 133MiB/s-133MiB/s (140MB/s-140MB/s), io=32.0GiB (34.4GB), run=246003-246003msec
(+23.1% throughput, -18.7% runtime)
************************
*** random writes ***
************************
==== 1 job, 8GiB file, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=11.5MiB/s (12.0MB/s), 11.5MiB/s-11.5MiB/s (12.0MB/s-12.0MB/s), io=8192MiB (8590MB), run=714281-714281msec
After patch:
WRITE: bw=11.6MiB/s (12.2MB/s), 11.6MiB/s-11.6MiB/s (12.2MB/s-12.2MB/s), io=8192MiB (8590MB), run=705959-705959msec
(+0.9% throughput, -1.7% runtime)
==== 2 jobs, 4GiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=12.8MiB/s (13.5MB/s), 12.8MiB/s-12.8MiB/s (13.5MB/s-13.5MB/s), io=8192MiB (8590MB), run=638101-638101msec
After patch:
WRITE: bw=13.1MiB/s (13.7MB/s), 13.1MiB/s-13.1MiB/s (13.7MB/s-13.7MB/s), io=8192MiB (8590MB), run=625374-625374msec
(+2.3% throughput, -2.0% runtime)
==== 4 jobs, 2GiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=15.4MiB/s (16.2MB/s), 15.4MiB/s-15.4MiB/s (16.2MB/s-16.2MB/s), io=8192MiB (8590MB), run=531146-531146msec
After patch:
WRITE: bw=17.8MiB/s (18.7MB/s), 17.8MiB/s-17.8MiB/s (18.7MB/s-18.7MB/s), io=8192MiB (8590MB), run=460431-460431msec
(+15.6% throughput, -13.3% runtime)
==== 8 jobs, 1GiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=19.9MiB/s (20.8MB/s), 19.9MiB/s-19.9MiB/s (20.8MB/s-20.8MB/s), io=8192MiB (8590MB), run=412664-412664msec
After patch:
WRITE: bw=22.2MiB/s (23.3MB/s), 22.2MiB/s-22.2MiB/s (23.3MB/s-23.3MB/s), io=8192MiB (8590MB), run=368589-368589msec
(+11.6% throughput, -10.7% runtime)
==== 16 jobs, 512MiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=29.3MiB/s (30.7MB/s), 29.3MiB/s-29.3MiB/s (30.7MB/s-30.7MB/s), io=8192MiB (8590MB), run=279924-279924msec
After patch:
WRITE: bw=30.4MiB/s (31.9MB/s), 30.4MiB/s-30.4MiB/s (31.9MB/s-31.9MB/s), io=8192MiB (8590MB), run=269258-269258msec
(+3.8% throughput, -3.8% runtime)
==== 32 jobs, 512MiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=36.9MiB/s (38.7MB/s), 36.9MiB/s-36.9MiB/s (38.7MB/s-38.7MB/s), io=16.0GiB (17.2GB), run=443581-443581msec
After patch:
WRITE: bw=41.6MiB/s (43.6MB/s), 41.6MiB/s-41.6MiB/s (43.6MB/s-43.6MB/s), io=16.0GiB (17.2GB), run=394114-394114msec
(+12.7% throughput, -11.2% runtime)
==== 64 jobs, 512MiB files, fsync frequency 16, block size 4KiB ====
Before patch:
WRITE: bw=45.9MiB/s (48.1MB/s), 45.9MiB/s-45.9MiB/s (48.1MB/s-48.1MB/s), io=32.0GiB (34.4GB), run=714614-714614msec
After patch:
WRITE: bw=48.8MiB/s (51.1MB/s), 48.8MiB/s-48.8MiB/s (51.1MB/s-51.1MB/s), io=32.0GiB (34.4GB), run=672087-672087msec
(+6.3% throughput, -6.0% runtime)
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Since commit d4682ba03e ("Btrfs: sync log after logging new name") we
started to commit logs, and fallback to transaction commits when we failed
to log the new names or commit the logs, after link and rename operations
when the target inodes (or their parents) were previously logged in the
current transaction. This was to avoid losing directories despite an
explicit fsync on them when they are ancestors of some inode that got a
new named logged, due to a link or rename operation. However that adds the
cost of starting IO and waiting for it to complete, which can cause higher
latencies for applications.
Instead of doing that, just make sure that when we log a new name for an
inode we don't mark any of its ancestors as logged, so that if any one
does an fsync against any of them, without doing any other change on them,
the fsync commits the log. This way we only pay the cost of a log commit
(or a transaction commit if something goes wrong or a new block group was
created) if the application explicitly asks to fsync any of the parent
directories.
Using dbench, which mixes several filesystems operations including renames,
revealed some significant latency gains. The following script that uses
dbench was used to test this:
#!/bin/bash
DEV=/dev/nvme0n1
MNT=/mnt/btrfs
MOUNT_OPTIONS="-o ssd -o space_cache=v2"
MKFS_OPTIONS="-m single -d single"
THREADS=16
echo "performance" | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
mkfs.btrfs -f $MKFS_OPTIONS $DEV
mount $MOUNT_OPTIONS $DEV $MNT
dbench -t 300 -D $MNT $THREADS
umount $MNT
The test was run on bare metal, no virtualization, on a box with 12 cores
(Intel i7-8700), 64Gb of RAM and using a NVMe device, with a kernel
configuration that is the default of typical distributions (debian in this
case), without debug options enabled (kasan, kmemleak, slub debug, debug
of page allocations, lock debugging, etc).
Results before this patch:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 10750455 0.011 155.088
Close 7896674 0.001 0.243
Rename 455222 2.158 1101.947
Unlink 2171189 0.067 121.638
Deltree 256 2.425 7.816
Mkdir 128 0.002 0.003
Qpathinfo 9744323 0.006 21.370
Qfileinfo 1707092 0.001 0.146
Qfsinfo 1786756 0.001 11.228
Sfileinfo 875612 0.003 21.263
Find 3767281 0.025 9.617
WriteX 5356924 0.011 211.390
ReadX 16852694 0.003 9.442
LockX 35008 0.002 0.119
UnlockX 35008 0.001 0.138
Flush 753458 4.252 1102.249
Throughput 1128.35 MB/sec 16 clients 16 procs max_latency=1102.255 ms
Results after this patch:
16 clients, after
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 11471098 0.012 448.281
Close 8426396 0.001 0.925
Rename 485746 0.123 267.183
Unlink 2316477 0.080 63.433
Deltree 288 2.830 11.144
Mkdir 144 0.003 0.010
Qpathinfo 10397420 0.006 10.288
Qfileinfo 1822039 0.001 0.169
Qfsinfo 1906497 0.002 14.039
Sfileinfo 934433 0.004 2.438
Find 4019879 0.026 10.200
WriteX 5718932 0.011 200.985
ReadX 17981671 0.003 10.036
LockX 37352 0.002 0.076
UnlockX 37352 0.001 0.109
Flush 804018 5.015 778.033
Throughput 1201.98 MB/sec 16 clients 16 procs max_latency=778.036 ms
(+6.5% throughput, -29.4% max latency, -75.8% rename latency)
Test case generic/498 from fstests tests the scenario that the previously
mentioned commit fixed.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During a rename we pin the log to make sure no one commits a log that
reflects an ongoing rename operation, as it might result in a committed
log where it recorded the unlink of the old name without having recorded
the new name. However we are taking the subvolume's log_mutex before
incrementing the log_writers counter, which is not necessary since that
counter is atomic and we only remove the old name from the log and add
the new name to the log after we have incremented log_writers, ensuring
that no one can commit the log after we have removed the old name from
the log and before we added the new name to the log.
By taking the log_mutex lock we are just adding unnecessary contention on
the lock, which can become visible for workloads that mix renames with
fsyncs, writes for files opened with O_SYNC and unlink operations (if the
inode or its parent were fsynced before in the current transaction).
So just remove the lock and unlock of the subvolume's log_mutex at
btrfs_pin_log_trans().
Using dbench, which mixes different types of operations that end up taking
that mutex (fsyncs, renames, unlinks and writes into files opened with
O_SYNC) revealed some small gains. The following script that calls dbench
was used:
#!/bin/bash
DEV=/dev/nvme0n1
MNT=/mnt/btrfs
MOUNT_OPTIONS="-o ssd -o space_cache=v2"
MKFS_OPTIONS="-m single -d single"
THREADS=32
echo "performance" | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
mkfs.btrfs -f $MKFS_OPTIONS $DEV
mount $MOUNT_OPTIONS $DEV $MNT
dbench -s -t 600 -D $MNT $THREADS
umount $MNT
The test was run on bare metal, no virtualization, on a box with 12 cores
(Intel i7-8700), 64Gb of RAM and using a NVMe device, with a kernel
configuration that is the default of typical distributions (debian in this
case), without debug options enabled (kasan, kmemleak, slub debug, debug
of page allocations, lock debugging, etc).
Results before this patch:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 4410848 0.017 738.640
Close 3240222 0.001 0.834
Rename 186850 7.478 1272.476
Unlink 890875 0.128 785.018
Deltree 128 2.846 12.081
Mkdir 64 0.002 0.003
Qpathinfo 3997659 0.009 11.171
Qfileinfo 701307 0.001 0.478
Qfsinfo 733494 0.002 1.103
Sfileinfo 359362 0.004 3.266
Find 1546226 0.041 4.128
WriteX 2202803 7.905 1376.989
ReadX 6917775 0.003 3.887
LockX 14392 0.002 0.043
UnlockX 14392 0.001 0.085
Flush 309225 0.128 1033.936
Throughput 231.555 MB/sec (sync open) 32 clients 32 procs max_latency=1376.993 ms
Results after this patch:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 4603244 0.017 232.776
Close 3381299 0.001 1.041
Rename 194871 7.251 1073.165
Unlink 929730 0.133 119.233
Deltree 128 2.871 10.199
Mkdir 64 0.002 0.004
Qpathinfo 4171343 0.009 11.317
Qfileinfo 731227 0.001 1.635
Qfsinfo 765079 0.002 3.568
Sfileinfo 374881 0.004 1.220
Find 1612964 0.041 4.675
WriteX 2296720 7.569 1178.204
ReadX 7213633 0.003 3.075
LockX 14976 0.002 0.076
UnlockX 14976 0.001 0.061
Flush 322635 0.102 579.505
Throughput 241.4 MB/sec (sync open) 32 clients 32 procs max_latency=1178.207 ms
(+4.3% throughput, -14.4% max latency)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There's a custom callback passed to btrfs_compare_trees which happens to
be named exactly same as the existing function implementing it. This is
confusing and the indirection is not necessary for our needs. Compiler
is clever enough to call it directly so there's effectively no change.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There's already defined _rs within ctree.h:btrfs_printk_ratelimited,
local variables should not use _ to avoid such name clashes with
macro-local variables.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In btrfs_orphan_cleanup, there's another instance of fs_info, but it's
the same as the one we already have.
In btrfs_backref_finish_upper_links, rb_node is same type and used
as temporary cursor to the tree.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The declarations of compression algorithm callbacks are defined in the
.c file as they're used from there. Compiler warns that there are no
declarations for public functions when compiling lzo.c/zlib.c/zstd.c.
Fix that by moving the declarations to the header as it's the common
place for all of them.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The function btrfs_feature_set_name returns a const char pointer, the
second const is not necessary and reported as a warning:
In file included from fs/btrfs/space-info.c:6:
fs/btrfs/sysfs.h:16:1: warning: type qualifiers ignored on function return type [-Wignored-qualifiers]
16 | const char * const btrfs_feature_set_name(enum btrfs_feature_set set);
| ^~~~~
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We're just doing rounding up to sectorsize to calculate the lockend.
There is no need to do the unnecessary length calculation, just direct
round_up() is enough.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Dave reported an issue where generic/102 would sometimes hang. This
turned out to be because we'd get into this spot where we were no longer
making progress on data reservations because our exit condition was not
met. The log is basically
while (!space_info->full && !list_empty(&space_info->tickets))
flush_space(space_info, flush_state);
where flush state is our various flush states, but doesn't include
ALLOC_CHUNK_FORCE. This is because we actually lead with allocating
chunks, and so the assumption was that once you got to the actual
flushing states you could no longer allocate chunks. This was a stupid
assumption, because you could have deleted block groups that would be
reclaimed by a transaction commit, thus unsetting space_info->full.
This is essentially what happens with generic/102, and so sometimes
you'd get stuck in the flushing loop because we weren't allocating
chunks, but flushing space wasn't giving us what we needed to make
progress.
Fix this by adding ALLOC_CHUNK_FORCE to the end of our flushing states,
that way we will eventually bail out because we did end up with
space_info->full if we free'd a chunk previously. Otherwise, as is the
case for this test, we'll allocate our chunk and continue on our happy
merry way.
Reported-by: David Sterba <dsterba@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The data flushing steps are not obvious to people other than myself and
Chris. Write a giant comment explaining the reasoning behind each flush
step for data as well as why it is in that particular order.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that we have the data ticketing stuff in place, move normal data
reservations to use an async reclaim helper to satisfy tickets. Before
we could have multiple tasks race in and both allocate chunks, resulting
in more data chunks than we would necessarily need. Serializing these
allocations and making a single thread responsible for flushing will
only allocate chunks as needed, as well as cut down on transaction
commits and other flush related activities.
Priority reservations will still work as they have before, simply
trying to allocate a chunk until they can make their reservation.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We can end up with freed extents in the delayed refs, and thus
may_commit_transaction() may not think we have enough pinned space to
commit the transaction and we'll ENOSPC early. Handle this by running
the delayed refs in order to make sure pinned is uptodate before we try
to commit the transaction.
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Before we were waiting on iputs after we committed the transaction, but
this doesn't really make much sense. We want to reclaim any space we
may have in order to be more likely to commit the transaction, due to
pinned space being added by running the delayed iputs. Fix this by
making delayed iputs run before committing the transaction.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We used to unconditionally commit the transaction at least 2 times and
then on the 3rd try check against pinned space to make sure committing
the transaction was worth the effort. This is overkill, we know nobody
is going to steal our reservation, and if we can't make our reservation
with the pinned amount simply bail out.
This also cleans up the passing of bytes_needed to
may_commit_transaction, as that was the thing we added into place in
order to accomplish this behavior. We no longer need it so remove that
mess.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This was an old wart left over from how we previously did data
reservations. Before we could have people race in and take a
reservation while we were flushing space, so we needed to make sure we
looped a few times before giving up. Now that we're using the ticketing
infrastructure we don't have to worry about this and can drop the logic
altogether.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that data reservations follow the same pattern as metadata
reservations we can simply rename __reserve_metadata_bytes to
__reserve_bytes and use that helper for data reservations.
Things to keep in mind, btrfs_can_overcommit() returns 0 for data,
because we can never overcommit. We also will never pass in FLUSH_ALL
for data, so we'll simply be added to the priority list and go straight
into handle_reserve_ticket.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Nikolay reported a problem where generic/371 would fail sometimes with a
slow drive. The gist of the test is that we fallocate a file in
parallel with a pwrite of a different file. These two files combined
are smaller than the file system, but sometimes the pwrite would ENOSPC.
A fair bit of investigation uncovered the fact that the fallocate
workload was racing in and grabbing the free space that the pwrite
workload was trying to free up so it could make its own reservation.
After a few loops of this eventually the pwrite workload would error out
with an ENOSPC.
We've had the same problem with metadata as well, and we serialized all
metadata allocations to satisfy this problem. This wasn't usually a
problem with data because data reservations are more straightforward,
but obviously could still happen.
Fix this by not allowing reservations to occur if there are any pending
tickets waiting to be satisfied on the space info.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that we have all the infrastructure in place, use the ticketing
infrastructure to make data allocations. This still maintains the exact
same flushing behavior, but now we're using tickets to get our
reservations satisfied.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Create a new function btrfs_reserve_data_bytes() in order to handle data
reservations. This uses the new flush types and flush states to handle
making data reservations.
This patch specifically does not change any functionality, and is
purposefully not cleaned up in order to make bisection easier for the
future patches. The new helper is identical to the old helper in how it
handles data reservations. We first try to force a chunk allocation,
and then we run through the flush states all at once and in the same
order that they were done with the old helper.
Subsequent patches will clean this up and change the behavior of the
flushing, and it is important to keep those changes separate so we can
easily bisect down to the patch that caused the regression, rather than
the patch that made us start using the new infrastructure.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Data space flushing currently unconditionally commits the transaction
twice in a row, and the last time it checks if there's enough pinned
extents to satisfy its reservation before deciding to commit the
transaction for the 3rd and final time.
Encode this logic into may_commit_transaction(). In the next patch we
will pass in U64_MAX for bytes_needed the first two times, and the final
time we will pass in the actual bytes we need so the normal logic will
apply.
This patch exists solely to make the logical changes I will make to the
flushing state machine separate to make it easier to bisect any
performance related regressions.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Currently the way we do data reservations is by seeing if we have enough
space in our space_info. If we do not and we're a normal inode we'll
1) Attempt to force a chunk allocation until we can't anymore.
2) If that fails we'll flush delalloc, then commit the transaction, then
run the delayed iputs.
If we are a free space inode we're only allowed to force a chunk
allocation. In order to use the normal flushing mechanism we need to
encode this into a flush state array for normal inodes. Since both will
start with allocating chunks until the space info is full there is no
need to add this as a flush state, this will be handled specially.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Right now if the space is freed up after the ordered extents complete
(which is likely since the reservations are held until they complete),
we would do extra delalloc flushing before we'd notice that we didn't
have any more tickets. Fix this by moving the tickets check after our
wait_ordered_extents check.
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The original iteration of flushing had us flushing delalloc and then
checking to see if we could make our reservation, thus we were very
careful about how many pages we would flush at once.
But now that everything is async and we satisfy tickets as the space
becomes available we don't have to keep track of any of this, simply
try and flush the number of dirty inodes we may have in order to
reclaim space to make our reservation. This cleans up our delalloc
flushing significantly.
The async_pages stuff is dropped because btrfs_start_delalloc_roots()
handles the case that we generate async extents for us, so we no longer
require this extra logic.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We are going to use the ticket infrastructure for data, so use the
btrfs_space_info_free_bytes_may_use() helper in
btrfs_free_reserved_data_space_noquota() so we get the
btrfs_try_granting_tickets call when we free our reservation.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If we have compression on we could free up more space than we reserved,
and thus be able to make a space reservation. Add the call for this
scenario.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When unpinning we were only calling btrfs_try_granting_tickets() if
global_rsv->space_info == space_info, which is problematic because we
use ticketing for SYSTEM chunks, and want to use it for DATA as well.
Fix this by moving this call outside of that if statement.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We were missing a call to btrfs_try_granting_tickets in
btrfs_free_reserved_bytes, so add it to handle the case where we're able
to satisfy an allocation because we've freed a pending reservation.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have traditionally used flush_space() to flush metadata space, so
we've been unconditionally using btrfs_metadata_alloc_profile() for our
profile to allocate a chunk. However if we're going to use this for
data we need to use btrfs_get_alloc_profile() on the space_info we pass
in.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Currently shrink_delalloc just looks up the metadata space info, but
this won't work if we're trying to reclaim space for data chunks. We
get the right space_info we want passed into flush_space, so simply pass
that along to shrink_delalloc.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Data allocations are going to want to pass in U64_MAX for flushing
space, adjust shrink_delalloc to handle this properly.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We don't use this anywhere inside of shrink_delalloc since 17024ad0a0
("Btrfs: fix early ENOSPC due to delalloc"), remove it.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have btrfs_wait_ordered_roots() which takes a u64 for nr, but
btrfs_start_delalloc_roots() that takes an int for nr, which makes using
them in conjunction, especially for something like (u64)-1, annoying and
inconsistent. Fix btrfs_start_delalloc_roots() to take a u64 for nr and
adjust start_delalloc_inodes() and it's callers appropriately.
This means we've adjusted start_delalloc_inodes() to take a pointer of
nr since we want to preserve the ability for start-delalloc_inodes() to
return an error, so simply make it do the nr adjusting as necessary.
Part of adjusting the callers to this means changing
btrfs_writeback_inodes_sb_nr() to take a u64 for items. This may be
confusing because it seems unrelated, but the caller of
btrfs_writeback_inodes_sb_nr() already passes in a u64, it's just the
function variable that needs to be changed.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It can be accessed from 'fs_devices' as it's identical to
fs_info->fs_devices. Also add a comment about why we are calling the
function. No semantic changes.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
That BUG_ON cannot ever trigger because as the comment there states -
'err' is always set. Simply remove it as it brings no value.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Delete repeated words in fs/btrfs/.
{to, the, a, and old}
and change "into 2 part" to "into 2 parts".
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The current trace event always output result like this:
find_free_extent: root=2(EXTENT_TREE) len=16384 empty_size=0 flags=4(METADATA)
find_free_extent: root=2(EXTENT_TREE) len=16384 empty_size=0 flags=4(METADATA)
find_free_extent: root=2(EXTENT_TREE) len=8192 empty_size=0 flags=1(DATA)
find_free_extent: root=2(EXTENT_TREE) len=8192 empty_size=0 flags=1(DATA)
find_free_extent: root=2(EXTENT_TREE) len=4096 empty_size=0 flags=1(DATA)
find_free_extent: root=2(EXTENT_TREE) len=4096 empty_size=0 flags=1(DATA)
T's saying we're allocating data extent for EXTENT tree, which is not
even possible.
It's because we always use EXTENT tree as the owner for
trace_find_free_extent() without using the @root from
btrfs_reserve_extent().
This patch will change the parameter to use proper @root for
trace_find_free_extent():
Now it looks much better:
find_free_extent: root=5(FS_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP)
find_free_extent: root=5(FS_TREE) len=8192 empty_size=0 flags=1(DATA)
find_free_extent: root=5(FS_TREE) len=16384 empty_size=0 flags=1(DATA)
find_free_extent: root=5(FS_TREE) len=4096 empty_size=0 flags=1(DATA)
find_free_extent: root=5(FS_TREE) len=8192 empty_size=0 flags=1(DATA)
find_free_extent: root=5(FS_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP)
find_free_extent: root=7(CSUM_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP)
find_free_extent: root=2(EXTENT_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP)
find_free_extent: root=1(ROOT_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP)
Reported-by: Hans van Kranenburg <hans@knorrie.org>
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----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=MT2i
-----END PGP SIGNATURE-----
Merge tag 'for-5.9-rc7-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
"Two more fixes.
One is for a lockdep warning/lockup (also caught by syzbot), that one
has been seen in practice. Regarding the other syzbot reports
mentioned last time, they don't seem to be urgent and reliably
reproducible so they'll be fixed later.
The second fix is for a potential corruption when device replace
finishes and the in-memory state of trim is not copied to the new
device"
* tag 'for-5.9-rc7-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: fix filesystem corruption after a device replace
btrfs: move btrfs_rm_dev_replace_free_srcdev outside of all locks
btrfs: move btrfs_scratch_superblocks into btrfs_dev_replace_finishing
We use a device's allocation state tree to track ranges in a device used
for allocated chunks, and we set ranges in this tree when allocating a new
chunk. However after a device replace operation, we were not setting the
allocated ranges in the new device's allocation state tree, so that tree
is empty after a device replace.
This means that a fitrim operation after a device replace will trim the
device ranges that have allocated chunks and extents, as we trim every
range for which there is not a range marked in the device's allocation
state tree. It is also important during chunk allocation, since the
device's allocation state is used to determine if a range is already
allocated when allocating a new chunk.
This is trivial to reproduce and the following script triggers the bug:
$ cat reproducer.sh
#!/bin/bash
DEV1="/dev/sdg"
DEV2="/dev/sdh"
DEV3="/dev/sdi"
wipefs -a $DEV1 $DEV2 $DEV3 &> /dev/null
# Create a raid1 test fs on 2 devices.
mkfs.btrfs -f -m raid1 -d raid1 $DEV1 $DEV2 > /dev/null
mount $DEV1 /mnt/btrfs
xfs_io -f -c "pwrite -S 0xab 0 10M" /mnt/btrfs/foo
echo "Starting to replace $DEV1 with $DEV3"
btrfs replace start -B $DEV1 $DEV3 /mnt/btrfs
echo
echo "Running fstrim"
fstrim /mnt/btrfs
echo
echo "Unmounting filesystem"
umount /mnt/btrfs
echo "Mounting filesystem in degraded mode using $DEV3 only"
wipefs -a $DEV1 $DEV2 &> /dev/null
mount -o degraded $DEV3 /mnt/btrfs
if [ $? -ne 0 ]; then
dmesg | tail
echo
echo "Failed to mount in degraded mode"
exit 1
fi
echo
echo "File foo data (expected all bytes = 0xab):"
od -A d -t x1 /mnt/btrfs/foo
umount /mnt/btrfs
When running the reproducer:
$ ./replace-test.sh
wrote 10485760/10485760 bytes at offset 0
10 MiB, 2560 ops; 0.0901 sec (110.877 MiB/sec and 28384.5216 ops/sec)
Starting to replace /dev/sdg with /dev/sdi
Running fstrim
Unmounting filesystem
Mounting filesystem in degraded mode using /dev/sdi only
mount: /mnt/btrfs: wrong fs type, bad option, bad superblock on /dev/sdi, missing codepage or helper program, or other error.
[19581.748641] BTRFS info (device sdg): dev_replace from /dev/sdg (devid 1) to /dev/sdi started
[19581.803842] BTRFS info (device sdg): dev_replace from /dev/sdg (devid 1) to /dev/sdi finished
[19582.208293] BTRFS info (device sdi): allowing degraded mounts
[19582.208298] BTRFS info (device sdi): disk space caching is enabled
[19582.208301] BTRFS info (device sdi): has skinny extents
[19582.212853] BTRFS warning (device sdi): devid 2 uuid 1f731f47-e1bb-4f00-bfbb-9e5a0cb4ba9f is missing
[19582.213904] btree_readpage_end_io_hook: 25839 callbacks suppressed
[19582.213907] BTRFS error (device sdi): bad tree block start, want 30490624 have 0
[19582.214780] BTRFS warning (device sdi): failed to read root (objectid=7): -5
[19582.231576] BTRFS error (device sdi): open_ctree failed
Failed to mount in degraded mode
So fix by setting all allocated ranges in the replace target device when
the replace operation is finishing, when we are holding the chunk mutex
and we can not race with new chunk allocations.
A test case for fstests follows soon.
Fixes: 1c11b63eff ("btrfs: replace pending/pinned chunks lists with io tree")
CC: stable@vger.kernel.org # 5.2+
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We need to move the closing of the src_device out of all the device
replace locking, but we definitely want to zero out the superblock
before we commit the last time to make sure the device is properly
removed. Handle this by pushing btrfs_scratch_superblocks into
btrfs_dev_replace_finishing, and then later on we'll move the src_device
closing and freeing stuff where we need it to be.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Just checking SB_I_CGROUPWB for cgroup writeback support is enough.
Either the file system allocates its own bdi (e.g. btrfs), in which case
it is known to support cgroup writeback, or the bdi comes from the block
layer, which always supports cgroup writeback.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Set up a readahead size by default, as very few users have a good
reason to change it. This means code, ecryptfs, and orangefs now
set up the values while they were previously missing it, while ubifs,
mtd and vboxsf manually set it to 0 to avoid readahead.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: David Sterba <dsterba@suse.com> [btrfs]
Acked-by: Richard Weinberger <richard@nod.at> [ubifs, mtd]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
-----BEGIN PGP SIGNATURE-----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=tFUE
-----END PGP SIGNATURE-----
Merge tag 'for-5.9-rc6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
"syzkaller started to hit us with reports, here's a fix for one type
(stack overflow when printing checksums on read error).
The other patch is a fix for sysfs object, we have a test for that and
it leads to a crash."
* tag 'for-5.9-rc6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: fix put of uninitialized kobject after seed device delete
btrfs: fix overflow when copying corrupt csums for a message
The following test case leads to NULL kobject free error:
mount seed /mnt
add sprout to /mnt
umount /mnt
mount sprout to /mnt
delete seed
kobject: '(null)' (00000000dd2b87e4): is not initialized, yet kobject_put() is being called.
WARNING: CPU: 1 PID: 15784 at lib/kobject.c:736 kobject_put+0x80/0x350
RIP: 0010:kobject_put+0x80/0x350
::
Call Trace:
btrfs_sysfs_remove_devices_dir+0x6e/0x160 [btrfs]
btrfs_rm_device.cold+0xa8/0x298 [btrfs]
btrfs_ioctl+0x206c/0x22a0 [btrfs]
ksys_ioctl+0xe2/0x140
__x64_sys_ioctl+0x1e/0x29
do_syscall_64+0x96/0x150
entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7f4047c6288b
::
This is because, at the end of the seed device-delete, we try to remove
the seed's devid sysfs entry. But for the seed devices under the sprout
fs, we don't initialize the devid kobject yet. So add a kobject state
check, which takes care of the bug.
Fixes: 668e48af7a ("btrfs: sysfs, add devid/dev_state kobject and device attributes")
CC: stable@vger.kernel.org # 5.6+
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----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=pdp0
-----END PGP SIGNATURE-----
Merge tag 'for-5.9-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fix from David Sterba:
"One of the recent lockdep fixes introduced a bug that breaks the
search ioctl, which is used by some applications (bees, compsize). The
patch made it to stable trees so we need this fixup to make it work
again"
* tag 'for-5.9-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: fix wrong address when faulting in pages in the search ioctl
When faulting in the pages for the user supplied buffer for the search
ioctl, we are passing only the base address of the buffer to the function
fault_in_pages_writeable(). This means that after the first iteration of
the while loop that searches for leaves, when we have a non-zero offset,
stored in 'sk_offset', we try to fault in a wrong page range.
So fix this by adding the offset in 'sk_offset' to the base address of the
user supplied buffer when calling fault_in_pages_writeable().
Several users have reported that the applications compsize and bees have
started to operate incorrectly since commit a48b73eca4 ("btrfs: fix
potential deadlock in the search ioctl") was added to stable trees, and
these applications make heavy use of the search ioctls. This fixes their
issues.
Link: https://lore.kernel.org/linux-btrfs/632b888d-a3c3-b085-cdf5-f9bb61017d92@lechevalier.se/
Link: https://github.com/kilobyte/compsize/issues/34
Fixes: a48b73eca4 ("btrfs: fix potential deadlock in the search ioctl")
CC: stable@vger.kernel.org # 4.4+
Tested-by: A L <mail@lechevalier.se>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----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=JTfF
-----END PGP SIGNATURE-----
Merge tag 'for-5.9-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
"A few more fixes:
- regression fix for a crash after failed snapshot creation
- one more lockep fix: use nofs allocation when allocating missing
device
- fix reloc tree leak on degraded mount
- make some extent buffer alignment checks less strict to mount
filesystems created by btrfs-convert"
* tag 'for-5.9-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: fix NULL pointer dereference after failure to create snapshot
btrfs: free data reloc tree on failed mount
btrfs: require only sector size alignment for parent eb bytenr
btrfs: fix lockdep splat in add_missing_dev
While testing a weird problem with -o degraded, I noticed I was getting
leaked root errors
BTRFS warning (device loop0): writable mount is not allowed due to too many missing devices
BTRFS error (device loop0): open_ctree failed
BTRFS error (device loop0): leaked root -9-0 refcount 1
This is the DATA_RELOC root, which gets read before the other fs roots,
but is included in the fs roots radix tree. Handle this by adding a
btrfs_drop_and_free_fs_root() on the data reloc root if it exists. This
is ok to do here if we fail further up because we will only drop the ref
if we delete the root from the radix tree, and all other cleanup won't
be duplicated.
CC: stable@vger.kernel.org # 5.8+
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
[BUG]
A completely sane converted fs will cause kernel warning at balance
time:
[ 1557.188633] BTRFS info (device sda7): relocating block group 8162107392 flags data
[ 1563.358078] BTRFS info (device sda7): found 11722 extents
[ 1563.358277] BTRFS info (device sda7): leaf 7989321728 gen 95 total ptrs 213 free space 3458 owner 2
[ 1563.358280] item 0 key (7984947200 169 0) itemoff 16250 itemsize 33
[ 1563.358281] extent refs 1 gen 90 flags 2
[ 1563.358282] ref#0: tree block backref root 4
[ 1563.358285] item 1 key (7985602560 169 0) itemoff 16217 itemsize 33
[ 1563.358286] extent refs 1 gen 93 flags 258
[ 1563.358287] ref#0: shared block backref parent 7985602560
[ 1563.358288] (parent 7985602560 is NOT ALIGNED to nodesize 16384)
[ 1563.358290] item 2 key (7985635328 169 0) itemoff 16184 itemsize 33
...
[ 1563.358995] BTRFS error (device sda7): eb 7989321728 invalid extent inline ref type 182
[ 1563.358996] ------------[ cut here ]------------
[ 1563.359005] WARNING: CPU: 14 PID: 2930 at 0xffffffff9f231766
Then with transaction abort, and obviously failed to balance the fs.
[CAUSE]
That mentioned inline ref type 182 is completely sane, it's
BTRFS_SHARED_BLOCK_REF_KEY, it's some extra check making kernel to
believe it's invalid.
Commit 64ecdb647d ("Btrfs: add one more sanity check for shared ref
type") introduced extra checks for backref type.
One of the requirement is, parent bytenr must be aligned to node size,
which is not correct.
One example is like this:
0 1G 1G+4K 2G 2G+4K
| |///////////////////|//| <- A chunk starts at 1G+4K
| | <- A tree block get reserved at bytenr 1G+4K
Then we have a valid tree block at bytenr 1G+4K, but not aligned to
nodesize (16K).
Such chunk is not ideal, but current kernel can handle it pretty well.
We may warn about such tree block in the future, but should not reject
them.
[FIX]
Change the alignment requirement from node size alignment to sector size
alignment.
Also, to make our lives a little easier, also output @iref when
btrfs_get_extent_inline_ref_type() failed, so we can locate the item
easier.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=205475
Fixes: 64ecdb647d ("Btrfs: add one more sanity check for shared ref type")
CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
[ update comments and messages ]
Signed-off-by: David Sterba <dsterba@suse.com>
Nikolay reported a lockdep splat in generic/476 that I could reproduce
with btrfs/187.
======================================================
WARNING: possible circular locking dependency detected
5.9.0-rc2+ #1 Tainted: G W
------------------------------------------------------
kswapd0/100 is trying to acquire lock:
ffff9e8ef38b6268 (&delayed_node->mutex){+.+.}-{3:3}, at: __btrfs_release_delayed_node.part.0+0x3f/0x330
but task is already holding lock:
ffffffffa9d74700 (fs_reclaim){+.+.}-{0:0}, at: __fs_reclaim_acquire+0x5/0x30
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (fs_reclaim){+.+.}-{0:0}:
fs_reclaim_acquire+0x65/0x80
slab_pre_alloc_hook.constprop.0+0x20/0x200
kmem_cache_alloc_trace+0x3a/0x1a0
btrfs_alloc_device+0x43/0x210
add_missing_dev+0x20/0x90
read_one_chunk+0x301/0x430
btrfs_read_sys_array+0x17b/0x1b0
open_ctree+0xa62/0x1896
btrfs_mount_root.cold+0x12/0xea
legacy_get_tree+0x30/0x50
vfs_get_tree+0x28/0xc0
vfs_kern_mount.part.0+0x71/0xb0
btrfs_mount+0x10d/0x379
legacy_get_tree+0x30/0x50
vfs_get_tree+0x28/0xc0
path_mount+0x434/0xc00
__x64_sys_mount+0xe3/0x120
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xa9
-> #1 (&fs_info->chunk_mutex){+.+.}-{3:3}:
__mutex_lock+0x7e/0x7e0
btrfs_chunk_alloc+0x125/0x3a0
find_free_extent+0xdf6/0x1210
btrfs_reserve_extent+0xb3/0x1b0
btrfs_alloc_tree_block+0xb0/0x310
alloc_tree_block_no_bg_flush+0x4a/0x60
__btrfs_cow_block+0x11a/0x530
btrfs_cow_block+0x104/0x220
btrfs_search_slot+0x52e/0x9d0
btrfs_lookup_inode+0x2a/0x8f
__btrfs_update_delayed_inode+0x80/0x240
btrfs_commit_inode_delayed_inode+0x119/0x120
btrfs_evict_inode+0x357/0x500
evict+0xcf/0x1f0
vfs_rmdir.part.0+0x149/0x160
do_rmdir+0x136/0x1a0
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xa9
-> #0 (&delayed_node->mutex){+.+.}-{3:3}:
__lock_acquire+0x1184/0x1fa0
lock_acquire+0xa4/0x3d0
__mutex_lock+0x7e/0x7e0
__btrfs_release_delayed_node.part.0+0x3f/0x330
btrfs_evict_inode+0x24c/0x500
evict+0xcf/0x1f0
dispose_list+0x48/0x70
prune_icache_sb+0x44/0x50
super_cache_scan+0x161/0x1e0
do_shrink_slab+0x178/0x3c0
shrink_slab+0x17c/0x290
shrink_node+0x2b2/0x6d0
balance_pgdat+0x30a/0x670
kswapd+0x213/0x4c0
kthread+0x138/0x160
ret_from_fork+0x1f/0x30
other info that might help us debug this:
Chain exists of:
&delayed_node->mutex --> &fs_info->chunk_mutex --> fs_reclaim
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(fs_reclaim);
lock(&fs_info->chunk_mutex);
lock(fs_reclaim);
lock(&delayed_node->mutex);
*** DEADLOCK ***
3 locks held by kswapd0/100:
#0: ffffffffa9d74700 (fs_reclaim){+.+.}-{0:0}, at: __fs_reclaim_acquire+0x5/0x30
#1: ffffffffa9d65c50 (shrinker_rwsem){++++}-{3:3}, at: shrink_slab+0x115/0x290
#2: ffff9e8e9da260e0 (&type->s_umount_key#48){++++}-{3:3}, at: super_cache_scan+0x38/0x1e0
stack backtrace:
CPU: 1 PID: 100 Comm: kswapd0 Tainted: G W 5.9.0-rc2+ #1
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
dump_stack+0x92/0xc8
check_noncircular+0x12d/0x150
__lock_acquire+0x1184/0x1fa0
lock_acquire+0xa4/0x3d0
? __btrfs_release_delayed_node.part.0+0x3f/0x330
__mutex_lock+0x7e/0x7e0
? __btrfs_release_delayed_node.part.0+0x3f/0x330
? __btrfs_release_delayed_node.part.0+0x3f/0x330
? lock_acquire+0xa4/0x3d0
? btrfs_evict_inode+0x11e/0x500
? find_held_lock+0x2b/0x80
__btrfs_release_delayed_node.part.0+0x3f/0x330
btrfs_evict_inode+0x24c/0x500
evict+0xcf/0x1f0
dispose_list+0x48/0x70
prune_icache_sb+0x44/0x50
super_cache_scan+0x161/0x1e0
do_shrink_slab+0x178/0x3c0
shrink_slab+0x17c/0x290
shrink_node+0x2b2/0x6d0
balance_pgdat+0x30a/0x670
kswapd+0x213/0x4c0
? _raw_spin_unlock_irqrestore+0x46/0x60
? add_wait_queue_exclusive+0x70/0x70
? balance_pgdat+0x670/0x670
kthread+0x138/0x160
? kthread_create_worker_on_cpu+0x40/0x40
ret_from_fork+0x1f/0x30
This is because we are holding the chunk_mutex when we call
btrfs_alloc_device, which does a GFP_KERNEL allocation. We don't want
to switch that to a GFP_NOFS lock because this is the only place where
it matters. So instead use memalloc_nofs_save() around the allocation
in order to avoid the lockdep splat.
Reported-by: Nikolay Borisov <nborisov@suse.com>
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----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=cdvW
-----END PGP SIGNATURE-----
Merge tag 'for-5.9-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
"Two small fixes and a bunch of lockdep fixes for warnings that show up
with an upcoming tree locking update but are valid with current locks
as well"
* tag 'for-5.9-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: tree-checker: fix the error message for transid error
btrfs: set the lockdep class for log tree extent buffers
btrfs: set the correct lockdep class for new nodes
btrfs: allocate scrub workqueues outside of locks
btrfs: fix potential deadlock in the search ioctl
btrfs: drop path before adding new uuid tree entry
btrfs: block-group: fix free-space bitmap threshold
The error message for inode transid is the same as for inode generation,
which makes us unable to detect the real problem.
Reported-by: Tyler Richmond <t.d.richmond@gmail.com>
Fixes: 496245cac5 ("btrfs: tree-checker: Verify inode item")
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Marcos Paulo de Souza <mpdesouza@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
These are special extent buffers that get rewound in order to lookup
the state of the tree at a specific point in time. As such they do not
go through the normal initialization paths that set their lockdep class,
so handle them appropriately when they are created and before they are
locked.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When flipping over to the rw_semaphore I noticed I'd get a lockdep splat
in replace_path(), which is weird because we're swapping the reloc root
with the actual target root. Turns out this is because we're using the
root->root_key.objectid as the root id for the newly allocated tree
block when setting the lockdep class, however we need to be using the
actual owner of this new block, which is saved in owner.
The affected path is through btrfs_copy_root as all other callers of
btrfs_alloc_tree_block (which calls init_new_buffer) have root_objectid
== root->root_key.objectid .
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
I got the following lockdep splat while testing:
======================================================
WARNING: possible circular locking dependency detected
5.8.0-rc7-00172-g021118712e59 #932 Not tainted
------------------------------------------------------
btrfs/229626 is trying to acquire lock:
ffffffff828513f0 (cpu_hotplug_lock){++++}-{0:0}, at: alloc_workqueue+0x378/0x450
but task is already holding lock:
ffff889dd3889518 (&fs_info->scrub_lock){+.+.}-{3:3}, at: btrfs_scrub_dev+0x11c/0x630
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #7 (&fs_info->scrub_lock){+.+.}-{3:3}:
__mutex_lock+0x9f/0x930
btrfs_scrub_dev+0x11c/0x630
btrfs_dev_replace_by_ioctl.cold.21+0x10a/0x1d4
btrfs_ioctl+0x2799/0x30a0
ksys_ioctl+0x83/0xc0
__x64_sys_ioctl+0x16/0x20
do_syscall_64+0x50/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xa9
-> #6 (&fs_devs->device_list_mutex){+.+.}-{3:3}:
__mutex_lock+0x9f/0x930
btrfs_run_dev_stats+0x49/0x480
commit_cowonly_roots+0xb5/0x2a0
btrfs_commit_transaction+0x516/0xa60
sync_filesystem+0x6b/0x90
generic_shutdown_super+0x22/0x100
kill_anon_super+0xe/0x30
btrfs_kill_super+0x12/0x20
deactivate_locked_super+0x29/0x60
cleanup_mnt+0xb8/0x140
task_work_run+0x6d/0xb0
__prepare_exit_to_usermode+0x1cc/0x1e0
do_syscall_64+0x5c/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xa9
-> #5 (&fs_info->tree_log_mutex){+.+.}-{3:3}:
__mutex_lock+0x9f/0x930
btrfs_commit_transaction+0x4bb/0xa60
sync_filesystem+0x6b/0x90
generic_shutdown_super+0x22/0x100
kill_anon_super+0xe/0x30
btrfs_kill_super+0x12/0x20
deactivate_locked_super+0x29/0x60
cleanup_mnt+0xb8/0x140
task_work_run+0x6d/0xb0
__prepare_exit_to_usermode+0x1cc/0x1e0
do_syscall_64+0x5c/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xa9
-> #4 (&fs_info->reloc_mutex){+.+.}-{3:3}:
__mutex_lock+0x9f/0x930
btrfs_record_root_in_trans+0x43/0x70
start_transaction+0xd1/0x5d0
btrfs_dirty_inode+0x42/0xd0
touch_atime+0xa1/0xd0
btrfs_file_mmap+0x3f/0x60
mmap_region+0x3a4/0x640
do_mmap+0x376/0x580
vm_mmap_pgoff+0xd5/0x120
ksys_mmap_pgoff+0x193/0x230
do_syscall_64+0x50/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xa9
-> #3 (&mm->mmap_lock#2){++++}-{3:3}:
__might_fault+0x68/0x90
_copy_to_user+0x1e/0x80
perf_read+0x141/0x2c0
vfs_read+0xad/0x1b0
ksys_read+0x5f/0xe0
do_syscall_64+0x50/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xa9
-> #2 (&cpuctx_mutex){+.+.}-{3:3}:
__mutex_lock+0x9f/0x930
perf_event_init_cpu+0x88/0x150
perf_event_init+0x1db/0x20b
start_kernel+0x3ae/0x53c
secondary_startup_64+0xa4/0xb0
-> #1 (pmus_lock){+.+.}-{3:3}:
__mutex_lock+0x9f/0x930
perf_event_init_cpu+0x4f/0x150
cpuhp_invoke_callback+0xb1/0x900
_cpu_up.constprop.26+0x9f/0x130
cpu_up+0x7b/0xc0
bringup_nonboot_cpus+0x4f/0x60
smp_init+0x26/0x71
kernel_init_freeable+0x110/0x258
kernel_init+0xa/0x103
ret_from_fork+0x1f/0x30
-> #0 (cpu_hotplug_lock){++++}-{0:0}:
__lock_acquire+0x1272/0x2310
lock_acquire+0x9e/0x360
cpus_read_lock+0x39/0xb0
alloc_workqueue+0x378/0x450
__btrfs_alloc_workqueue+0x15d/0x200
btrfs_alloc_workqueue+0x51/0x160
scrub_workers_get+0x5a/0x170
btrfs_scrub_dev+0x18c/0x630
btrfs_dev_replace_by_ioctl.cold.21+0x10a/0x1d4
btrfs_ioctl+0x2799/0x30a0
ksys_ioctl+0x83/0xc0
__x64_sys_ioctl+0x16/0x20
do_syscall_64+0x50/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xa9
other info that might help us debug this:
Chain exists of:
cpu_hotplug_lock --> &fs_devs->device_list_mutex --> &fs_info->scrub_lock
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&fs_info->scrub_lock);
lock(&fs_devs->device_list_mutex);
lock(&fs_info->scrub_lock);
lock(cpu_hotplug_lock);
*** DEADLOCK ***
2 locks held by btrfs/229626:
#0: ffff88bfe8bb86e0 (&fs_devs->device_list_mutex){+.+.}-{3:3}, at: btrfs_scrub_dev+0xbd/0x630
#1: ffff889dd3889518 (&fs_info->scrub_lock){+.+.}-{3:3}, at: btrfs_scrub_dev+0x11c/0x630
stack backtrace:
CPU: 15 PID: 229626 Comm: btrfs Kdump: loaded Not tainted 5.8.0-rc7-00172-g021118712e59 #932
Hardware name: Quanta Tioga Pass Single Side 01-0030993006/Tioga Pass Single Side, BIOS F08_3A18 12/20/2018
Call Trace:
dump_stack+0x78/0xa0
check_noncircular+0x165/0x180
__lock_acquire+0x1272/0x2310
lock_acquire+0x9e/0x360
? alloc_workqueue+0x378/0x450
cpus_read_lock+0x39/0xb0
? alloc_workqueue+0x378/0x450
alloc_workqueue+0x378/0x450
? rcu_read_lock_sched_held+0x52/0x80
__btrfs_alloc_workqueue+0x15d/0x200
btrfs_alloc_workqueue+0x51/0x160
scrub_workers_get+0x5a/0x170
btrfs_scrub_dev+0x18c/0x630
? start_transaction+0xd1/0x5d0
btrfs_dev_replace_by_ioctl.cold.21+0x10a/0x1d4
btrfs_ioctl+0x2799/0x30a0
? do_sigaction+0x102/0x250
? lockdep_hardirqs_on_prepare+0xca/0x160
? _raw_spin_unlock_irq+0x24/0x30
? trace_hardirqs_on+0x1c/0xe0
? _raw_spin_unlock_irq+0x24/0x30
? do_sigaction+0x102/0x250
? ksys_ioctl+0x83/0xc0
ksys_ioctl+0x83/0xc0
__x64_sys_ioctl+0x16/0x20
do_syscall_64+0x50/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xa9
This happens because we're allocating the scrub workqueues under the
scrub and device list mutex, which brings in a whole host of other
dependencies.
Because the work queue allocation is done with GFP_KERNEL, it can
trigger reclaim, which can lead to a transaction commit, which in turns
needs the device_list_mutex, it can lead to a deadlock. A different
problem for which this fix is a solution.
Fix this by moving the actual allocation outside of the
scrub lock, and then only take the lock once we're ready to actually
assign them to the fs_info. We'll now have to cleanup the workqueues in
a few more places, so I've added a helper to do the refcount dance to
safely free the workqueues.
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
With the conversion of the tree locks to rwsem I got the following
lockdep splat:
======================================================
WARNING: possible circular locking dependency detected
5.8.0-rc7-00165-g04ec4da5f45f-dirty #922 Not tainted
------------------------------------------------------
compsize/11122 is trying to acquire lock:
ffff889fabca8768 (&mm->mmap_lock#2){++++}-{3:3}, at: __might_fault+0x3e/0x90
but task is already holding lock:
ffff889fe720fe40 (btrfs-fs-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x39/0x180
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (btrfs-fs-00){++++}-{3:3}:
down_write_nested+0x3b/0x70
__btrfs_tree_lock+0x24/0x120
btrfs_search_slot+0x756/0x990
btrfs_lookup_inode+0x3a/0xb4
__btrfs_update_delayed_inode+0x93/0x270
btrfs_async_run_delayed_root+0x168/0x230
btrfs_work_helper+0xd4/0x570
process_one_work+0x2ad/0x5f0
worker_thread+0x3a/0x3d0
kthread+0x133/0x150
ret_from_fork+0x1f/0x30
-> #1 (&delayed_node->mutex){+.+.}-{3:3}:
__mutex_lock+0x9f/0x930
btrfs_delayed_update_inode+0x50/0x440
btrfs_update_inode+0x8a/0xf0
btrfs_dirty_inode+0x5b/0xd0
touch_atime+0xa1/0xd0
btrfs_file_mmap+0x3f/0x60
mmap_region+0x3a4/0x640
do_mmap+0x376/0x580
vm_mmap_pgoff+0xd5/0x120
ksys_mmap_pgoff+0x193/0x230
do_syscall_64+0x50/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xa9
-> #0 (&mm->mmap_lock#2){++++}-{3:3}:
__lock_acquire+0x1272/0x2310
lock_acquire+0x9e/0x360
__might_fault+0x68/0x90
_copy_to_user+0x1e/0x80
copy_to_sk.isra.32+0x121/0x300
search_ioctl+0x106/0x200
btrfs_ioctl_tree_search_v2+0x7b/0xf0
btrfs_ioctl+0x106f/0x30a0
ksys_ioctl+0x83/0xc0
__x64_sys_ioctl+0x16/0x20
do_syscall_64+0x50/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xa9
other info that might help us debug this:
Chain exists of:
&mm->mmap_lock#2 --> &delayed_node->mutex --> btrfs-fs-00
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(btrfs-fs-00);
lock(&delayed_node->mutex);
lock(btrfs-fs-00);
lock(&mm->mmap_lock#2);
*** DEADLOCK ***
1 lock held by compsize/11122:
#0: ffff889fe720fe40 (btrfs-fs-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x39/0x180
stack backtrace:
CPU: 17 PID: 11122 Comm: compsize Kdump: loaded Not tainted 5.8.0-rc7-00165-g04ec4da5f45f-dirty #922
Hardware name: Quanta Tioga Pass Single Side 01-0030993006/Tioga Pass Single Side, BIOS F08_3A18 12/20/2018
Call Trace:
dump_stack+0x78/0xa0
check_noncircular+0x165/0x180
__lock_acquire+0x1272/0x2310
lock_acquire+0x9e/0x360
? __might_fault+0x3e/0x90
? find_held_lock+0x72/0x90
__might_fault+0x68/0x90
? __might_fault+0x3e/0x90
_copy_to_user+0x1e/0x80
copy_to_sk.isra.32+0x121/0x300
? btrfs_search_forward+0x2a6/0x360
search_ioctl+0x106/0x200
btrfs_ioctl_tree_search_v2+0x7b/0xf0
btrfs_ioctl+0x106f/0x30a0
? __do_sys_newfstat+0x5a/0x70
? ksys_ioctl+0x83/0xc0
ksys_ioctl+0x83/0xc0
__x64_sys_ioctl+0x16/0x20
do_syscall_64+0x50/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xa9
The problem is we're doing a copy_to_user() while holding tree locks,
which can deadlock if we have to do a page fault for the copy_to_user().
This exists even without my locking changes, so it needs to be fixed.
Rework the search ioctl to do the pre-fault and then
copy_to_user_nofault for the copying.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
With the conversion of the tree locks to rwsem I got the following
lockdep splat:
======================================================
WARNING: possible circular locking dependency detected
5.8.0-rc7-00167-g0d7ba0c5b375-dirty #925 Not tainted
------------------------------------------------------
btrfs-uuid/7955 is trying to acquire lock:
ffff88bfbafec0f8 (btrfs-root-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x39/0x180
but task is already holding lock:
ffff88bfbafef2a8 (btrfs-uuid-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x39/0x180
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (btrfs-uuid-00){++++}-{3:3}:
down_read_nested+0x3e/0x140
__btrfs_tree_read_lock+0x39/0x180
__btrfs_read_lock_root_node+0x3a/0x50
btrfs_search_slot+0x4bd/0x990
btrfs_uuid_tree_add+0x89/0x2d0
btrfs_uuid_scan_kthread+0x330/0x390
kthread+0x133/0x150
ret_from_fork+0x1f/0x30
-> #0 (btrfs-root-00){++++}-{3:3}:
__lock_acquire+0x1272/0x2310
lock_acquire+0x9e/0x360
down_read_nested+0x3e/0x140
__btrfs_tree_read_lock+0x39/0x180
__btrfs_read_lock_root_node+0x3a/0x50
btrfs_search_slot+0x4bd/0x990
btrfs_find_root+0x45/0x1b0
btrfs_read_tree_root+0x61/0x100
btrfs_get_root_ref.part.50+0x143/0x630
btrfs_uuid_tree_iterate+0x207/0x314
btrfs_uuid_rescan_kthread+0x12/0x50
kthread+0x133/0x150
ret_from_fork+0x1f/0x30
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(btrfs-uuid-00);
lock(btrfs-root-00);
lock(btrfs-uuid-00);
lock(btrfs-root-00);
*** DEADLOCK ***
1 lock held by btrfs-uuid/7955:
#0: ffff88bfbafef2a8 (btrfs-uuid-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x39/0x180
stack backtrace:
CPU: 73 PID: 7955 Comm: btrfs-uuid Kdump: loaded Not tainted 5.8.0-rc7-00167-g0d7ba0c5b375-dirty #925
Hardware name: Quanta Tioga Pass Single Side 01-0030993006/Tioga Pass Single Side, BIOS F08_3A18 12/20/2018
Call Trace:
dump_stack+0x78/0xa0
check_noncircular+0x165/0x180
__lock_acquire+0x1272/0x2310
lock_acquire+0x9e/0x360
? __btrfs_tree_read_lock+0x39/0x180
? btrfs_root_node+0x1c/0x1d0
down_read_nested+0x3e/0x140
? __btrfs_tree_read_lock+0x39/0x180
__btrfs_tree_read_lock+0x39/0x180
__btrfs_read_lock_root_node+0x3a/0x50
btrfs_search_slot+0x4bd/0x990
btrfs_find_root+0x45/0x1b0
btrfs_read_tree_root+0x61/0x100
btrfs_get_root_ref.part.50+0x143/0x630
btrfs_uuid_tree_iterate+0x207/0x314
? btree_readpage+0x20/0x20
btrfs_uuid_rescan_kthread+0x12/0x50
kthread+0x133/0x150
? kthread_create_on_node+0x60/0x60
ret_from_fork+0x1f/0x30
This problem exists because we have two different rescan threads,
btrfs_uuid_scan_kthread which creates the uuid tree, and
btrfs_uuid_tree_iterate that goes through and updates or deletes any out
of date roots. The problem is they both do things in different order.
btrfs_uuid_scan_kthread() reads the tree_root, and then inserts entries
into the uuid_root. btrfs_uuid_tree_iterate() scans the uuid_root, but
then does a btrfs_get_fs_root() which can read from the tree_root.
It's actually easy enough to not be holding the path in
btrfs_uuid_scan_kthread() when we add a uuid entry, as we already drop
it further down and re-start the search when we loop. So simply move
the path release before we add our entry to the uuid tree.
This also fixes a problem where we're holding a path open after we do
btrfs_end_transaction(), which has it's own problems.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
[BUG]
After commit 9afc66498a ("btrfs: block-group: refactor how we read one
block group item"), cache->length is being assigned after calling
btrfs_create_block_group_cache. This causes a problem since
set_free_space_tree_thresholds calculates the free-space threshold to
decide if the free-space tree should convert from extents to bitmaps.
The current code calls set_free_space_tree_thresholds with cache->length
being 0, which then makes cache->bitmap_high_thresh zero. This implies
the system will always use bitmap instead of extents, which is not
desired if the block group is not fragmented.
This behavior can be seen by a test that expects to repair systems
with FREE_SPACE_EXTENT and FREE_SPACE_BITMAP, but the current code only
created FREE_SPACE_BITMAP.
[FIX]
Call set_free_space_tree_thresholds after setting cache->length. There
is now a WARN_ON in set_free_space_tree_thresholds to help preventing
the same mistake to happen again in the future.
Link: https://github.com/kdave/btrfs-progs/issues/251
Fixes: 9afc66498a ("btrfs: block-group: refactor how we read one block group item")
CC: stable@vger.kernel.org # 5.8+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Marcos Paulo de Souza <mpdesouza@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----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=ONgI
-----END PGP SIGNATURE-----
Merge tag 'for-5.9-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
- fix swapfile activation on subvolumes with deleted snapshots
- error value mixup when removing directory entries from tree log
- fix lzo compression level reset after previous level setting
- fix space cache memory leak after transaction abort
- fix const function attribute
- more error handling improvements
* tag 'for-5.9-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: detect nocow for swap after snapshot delete
btrfs: check the right error variable in btrfs_del_dir_entries_in_log
btrfs: fix space cache memory leak after transaction abort
btrfs: use the correct const function attribute for btrfs_get_num_csums
btrfs: reset compression level for lzo on remount
btrfs: handle errors from async submission
can_nocow_extent and btrfs_cross_ref_exist both rely on a heuristic for
detecting a must cow condition which is not exactly accurate, but saves
unnecessary tree traversal. The incorrect assumption is that if the
extent was created in a generation smaller than the last snapshot
generation, it must be referenced by that snapshot. That is true, except
the snapshot could have since been deleted, without affecting the last
snapshot generation.
The original patch claimed a performance win from this check, but it
also leads to a bug where you are unable to use a swapfile if you ever
snapshotted the subvolume it's in. Make the check slower and more strict
for the swapon case, without modifying the general cow checks as a
compromise. Turning swap on does not seem to be a particularly
performance sensitive operation, so incurring a possibly unnecessary
btrfs_search_slot seems worthwhile for the added usability.
Note: Until the snapshot is competely cleaned after deletion,
check_committed_refs will still cause the logic to think that cow is
necessary, so the user must until 'btrfs subvolu sync' finished before
activating the swapfile swapon.
CC: stable@vger.kernel.org # 5.4+
Suggested-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
With my new locking code dbench is so much faster that I tripped over a
transaction abort from ENOSPC. This turned out to be because
btrfs_del_dir_entries_in_log was checking for ret == -ENOSPC, but this
function sets err on error, and returns err. So instead of properly
marking the inode as needing a full commit, we were returning -ENOSPC
and aborting in __btrfs_unlink_inode. Fix this by checking the proper
variable so that we return the correct thing in the case of ENOSPC.
The ENOENT needs to be checked, because btrfs_lookup_dir_item_index()
can return -ENOENT if the dir item isn't in the tree log (which would
happen if we hadn't fsync'ed this guy). We actually handle that case in
__btrfs_unlink_inode, so it's an expected error to get back.
Fixes: 4a500fd178 ("Btrfs: Metadata ENOSPC handling for tree log")
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ add note and comment about ENOENT ]
Signed-off-by: David Sterba <dsterba@suse.com>
If a transaction aborts it can cause a memory leak of the pages array of
a block group's io_ctl structure. The following steps explain how that can
happen:
1) Transaction N is committing, currently in state TRANS_STATE_UNBLOCKED
and it's about to start writing out dirty extent buffers;
2) Transaction N + 1 already started and another task, task A, just called
btrfs_commit_transaction() on it;
3) Block group B was dirtied (extents allocated from it) by transaction
N + 1, so when task A calls btrfs_start_dirty_block_groups(), at the
very beginning of the transaction commit, it starts writeback for the
block group's space cache by calling btrfs_write_out_cache(), which
allocates the pages array for the block group's io_ctl with a call to
io_ctl_init(). Block group A is added to the io_list of transaction
N + 1 by btrfs_start_dirty_block_groups();
4) While transaction N's commit is writing out the extent buffers, it gets
an IO error and aborts transaction N, also setting the file system to
RO mode;
5) Task A has already returned from btrfs_start_dirty_block_groups(), is at
btrfs_commit_transaction() and has set transaction N + 1 state to
TRANS_STATE_COMMIT_START. Immediately after that it checks that the
filesystem was turned to RO mode, due to transaction N's abort, and
jumps to the "cleanup_transaction" label. After that we end up at
btrfs_cleanup_one_transaction() which calls btrfs_cleanup_dirty_bgs().
That helper finds block group B in the transaction's io_list but it
never releases the pages array of the block group's io_ctl, resulting in
a memory leak.
In fact at the point when we are at btrfs_cleanup_dirty_bgs(), the pages
array points to pages that were already released by us at
__btrfs_write_out_cache() through the call to io_ctl_drop_pages(). We end
up freeing the pages array only after waiting for the ordered extent to
complete through btrfs_wait_cache_io(), which calls io_ctl_free() to do
that. But in the transaction abort case we don't wait for the space cache's
ordered extent to complete through a call to btrfs_wait_cache_io(), so
that's why we end up with a memory leak - we wait for the ordered extent
to complete indirectly by shutting down the work queues and waiting for
any jobs in them to complete before returning from close_ctree().
We can solve the leak simply by freeing the pages array right after
releasing the pages (with the call to io_ctl_drop_pages()) at
__btrfs_write_out_cache(), since we will never use it anymore after that
and the pages array points to already released pages at that point, which
is currently not a problem since no one will use it after that, but not a
good practice anyway since it can easily lead to use-after-free issues.
So fix this by freeing the pages array right after releasing the pages at
__btrfs_write_out_cache().
This issue can often be reproduced with test case generic/475 from fstests
and kmemleak can detect it and reports it with the following trace:
unreferenced object 0xffff9bbf009fa600 (size 512):
comm "fsstress", pid 38807, jiffies 4298504428 (age 22.028s)
hex dump (first 32 bytes):
00 a0 7c 4d 3d ed ff ff 40 a0 7c 4d 3d ed ff ff ..|M=...@.|M=...
80 a0 7c 4d 3d ed ff ff c0 a0 7c 4d 3d ed ff ff ..|M=.....|M=...
backtrace:
[<00000000f4b5cfe2>] __kmalloc+0x1a8/0x3e0
[<0000000028665e7f>] io_ctl_init+0xa7/0x120 [btrfs]
[<00000000a1f95b2d>] __btrfs_write_out_cache+0x86/0x4a0 [btrfs]
[<00000000207ea1b0>] btrfs_write_out_cache+0x7f/0xf0 [btrfs]
[<00000000af21f534>] btrfs_start_dirty_block_groups+0x27b/0x580 [btrfs]
[<00000000c3c23d44>] btrfs_commit_transaction+0xa6f/0xe70 [btrfs]
[<000000009588930c>] create_subvol+0x581/0x9a0 [btrfs]
[<000000009ef2fd7f>] btrfs_mksubvol+0x3fb/0x4a0 [btrfs]
[<00000000474e5187>] __btrfs_ioctl_snap_create+0x119/0x1a0 [btrfs]
[<00000000708ee349>] btrfs_ioctl_snap_create_v2+0xb0/0xf0 [btrfs]
[<00000000ea60106f>] btrfs_ioctl+0x12c/0x3130 [btrfs]
[<000000005c923d6d>] __x64_sys_ioctl+0x83/0xb0
[<0000000043ace2c9>] do_syscall_64+0x33/0x80
[<00000000904efbce>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
CC: stable@vger.kernel.org # 4.9+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The build robot reports
compiler: h8300-linux-gcc (GCC) 9.3.0
In file included from fs/btrfs/tests/extent-map-tests.c:8:
>> fs/btrfs/tests/../ctree.h:2166:8: warning: type qualifiers ignored on function return type [-Wignored-qualifiers]
2166 | size_t __const btrfs_get_num_csums(void);
| ^~~~~~~
The function attribute for const does not follow the expected scheme and
in this case is confused with a const type qualifier.
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Currently a user can set mount "-o compress" which will set the
compression algorithm to zlib, and use the default compress level for
zlib (3):
relatime,compress=zlib:3,space_cache
If the user remounts the fs using "-o compress=lzo", then the old
compress_level is used:
relatime,compress=lzo:3,space_cache
But lzo does not expose any tunable compression level. The same happens
if we set any compress argument with different level, also with zstd.
Fix this by resetting the compress_level when compress=lzo is
specified. With the fix applied, lzo is shown without compress level:
relatime,compress=lzo,space_cache
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Marcos Paulo de Souza <mpdesouza@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Btrfs' async submit mechanism is able to handle errors in the submission
path and the meta-data async submit function correctly passes the error
code to the caller.
In btrfs_submit_bio_start() and btrfs_submit_bio_start_direct_io() we're
not handling the errors returned by btrfs_csum_one_bio() correctly though
and simply call BUG_ON(). This is unnecessary as the caller of these two
functions - run_one_async_start - correctly checks for the return values
and sets the status of the async_submit_bio. The actual bio submission
will be handled later on by run_one_async_done only if
async_submit_bio::status is 0, so the data won't be written if we
encountered an error in the checksum process.
Simply return the error from btrfs_csum_one_bio() to the async submitters,
like it's done in btree_submit_bio_start().
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----
iQIzBAABCgAdFiEE8rQSAMVO+zA4DBdWxWXV+ddtWDsFAl81Q0wACgkQxWXV+ddt
WDtbqw/+NeFlvQzsCeQV9PX7RjYf9MFEQIThxo33xDl+ersgcOD8MuPa/hY1hoO0
gOn2eRPcVe/RIPBezRbxX9bnqlfW6N0VnBNLJHypMapB2hR6WFcFt7CAMoXKRmHV
RDM37pA2TNULr8XYrJ0+J5Vy1NWp5HdKzEV6bXfsOSzMSdAVMheXNec93suLEB/g
9QGXX6kaaq0Hcpy7tQQBtm2lbVj8/M3LOUAmYOB/JNCPtsJEB/2EO2b63TB4s2cW
0lpiPehW2m/Pv5GjqQM+iN5fbt9yhKB6lqEEgoHZPgI2tLFyh5WlTWKET7uxqj7G
YBzZjiq1WREEl9KWLYZuthcXPLX2XgJ4gLSlckygi1e4MpPlJ4pa30Bj9OyIEIjP
FOeR0lelRYcjmZrQW4Kana0qq8K0JJzvo2dSqaJBGF9CaveN3BAGQ9ttNhgIIpS5
4kBKlv2SCJ9Anhn8la6bFwlfuR2ggMhDShxIGBQpA1OKf0oJyi2dtavSIbuXwFbd
6KA37cyp4cDK9ycmTN5YxZSndzZSqUEh5Wt4gLk32NeIxhyCX4aTvjQj5KqM1MNw
N/WrTJQ27D6jfi+PBRBmT7U6qEujySXUimJRFTJzk+Px8Q/QMzGAFPCqz6iXv3u3
lX1Ywha9iQ0g2IZVoaq1ZjDDp4xOqIakAjaXez3dFhu3Mq3Kc70=
=7b8U
-----END PGP SIGNATURE-----
Merge tag 'for-5.9-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull more btrfs updates from David Sterba:
"One minor update, the rest are fixes that have arrived a bit late for
the first batch. There are also some recent fixes for bugs that were
discovered during the merge window and pop up during testing.
User visible change:
- show correct subvolume path in /proc/mounts for bind mounts
Fixes:
- fix compression messages when remounting with different level or
compression algorithm
- tree-log: fix some memory leaks on error handling paths
- restore I_VERSION on remount
- fix return values and error code mixups
- fix umount crash with quotas enabled when removing sysfs files
- fix trim range on a shrunk device"
* tag 'for-5.9-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: trim: fix underflow in trim length to prevent access beyond device boundary
btrfs: fix return value mixup in btrfs_get_extent
btrfs: sysfs: fix NULL pointer dereference at btrfs_sysfs_del_qgroups()
btrfs: check correct variable after allocation in btrfs_backref_iter_alloc
btrfs: make sure SB_I_VERSION doesn't get unset by remount
btrfs: fix memory leaks after failure to lookup checksums during inode logging
btrfs: don't show full path of bind mounts in subvol=
btrfs: fix messages after changing compression level by remount
btrfs: only search for left_info if there is no right_info in try_merge_free_space
btrfs: inode: fix NULL pointer dereference if inode doesn't need compression
[BUG]
The following script can lead to tons of beyond device boundary access:
mkfs.btrfs -f $dev -b 10G
mount $dev $mnt
trimfs $mnt
btrfs filesystem resize 1:-1G $mnt
trimfs $mnt
[CAUSE]
Since commit 929be17a9b ("btrfs: Switch btrfs_trim_free_extents to
find_first_clear_extent_bit"), we try to avoid trimming ranges that's
already trimmed.
So we check device->alloc_state by finding the first range which doesn't
have CHUNK_TRIMMED and CHUNK_ALLOCATED not set.
But if we shrunk the device, that bits are not cleared, thus we could
easily got a range starts beyond the shrunk device size.
This results the returned @start and @end are all beyond device size,
then we call "end = min(end, device->total_bytes -1);" making @end
smaller than device size.
Then finally we goes "len = end - start + 1", totally underflow the
result, and lead to the beyond-device-boundary access.
[FIX]
This patch will fix the problem in two ways:
- Clear CHUNK_TRIMMED | CHUNK_ALLOCATED bits when shrinking device
This is the root fix
- Add extra safety check when trimming free device extents
We check and warn if the returned range is already beyond current
device.
Link: https://github.com/kdave/btrfs-progs/issues/282
Fixes: 929be17a9b ("btrfs: Switch btrfs_trim_free_extents to find_first_clear_extent_bit")
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
btrfs_get_extent() sets variable ret, but out: error path expect error
to be in variable err so the error code is lost.
Fixes: 6bf9e4bd6a ("btrfs: inode: Verify inode mode to avoid NULL pointer dereference")
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Pavel Machek (CIP) <pavel@denx.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
[BUG]
Unmounting a btrfs filesystem with quota disabled will cause the
following NULL pointer dereference:
BTRFS info (device dm-5): has skinny extents
BUG: kernel NULL pointer dereference, address: 0000000000000018
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
CPU: 7 PID: 637 Comm: umount Not tainted 5.8.0-rc7-next-20200731-custom #76
RIP: 0010:kobject_del+0x6/0x20
Call Trace:
btrfs_sysfs_del_qgroups+0xac/0xf0 [btrfs]
btrfs_free_qgroup_config+0x63/0x70 [btrfs]
close_ctree+0x1f5/0x323 [btrfs]
btrfs_put_super+0x15/0x17 [btrfs]
generic_shutdown_super+0x72/0x110
kill_anon_super+0x18/0x30
btrfs_kill_super+0x17/0x30 [btrfs]
deactivate_locked_super+0x3b/0xa0
deactivate_super+0x40/0x50
cleanup_mnt+0x135/0x190
__cleanup_mnt+0x12/0x20
task_work_run+0x64/0xb0
exit_to_user_mode_prepare+0x18a/0x190
syscall_exit_to_user_mode+0x4f/0x270
do_syscall_64+0x45/0x50
entry_SYSCALL_64_after_hwframe+0x44/0xa9
---[ end trace 37b7adca5c1d5c5d ]---
[CAUSE]
Commit 079ad2fb4b ("kobject: Avoid premature parent object freeing in
kobject_cleanup()") changed kobject_del() that it no longer accepts NULL
pointer.
Before that commit, kobject_del() and kobject_put() all accept NULL
pointers and just ignore such NULL pointers.
But that mentioned commit needs to access the parent node, killing the
old NULL pointer behavior.
Unfortunately btrfs is relying on that hidden feature thus we will
trigger such NULL pointer dereference.
[FIX]
Instead of just saving several lines, do proper fs_info->qgroups_kobj
check before calling kobject_del() and kobject_put().
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The `if (!ret)` check will always be false and it may result in
ret->path being dereferenced while it is a NULL pointer.
Fixes: a37f232b7b ("btrfs: backref: introduce the skeleton of btrfs_backref_iter")
CC: stable@vger.kernel.org # 5.8+
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Boleyn Su <boleynsu@google.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There's some inconsistency around SB_I_VERSION handling with mount and
remount. Since we don't really want it to be off ever just work around
this by making sure we don't get the flag cleared on remount.
There's a tiny cpu cost of setting the bit, otherwise all changes to
i_version also change some of the times (ctime/mtime) so the inode needs
to be synced. We wouldn't save anything by disabling it.
Reported-by: Eric Sandeen <sandeen@redhat.com>
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ add perf impact analysis ]
Signed-off-by: David Sterba <dsterba@suse.com>
While logging an inode, at copy_items(), if we fail to lookup the checksums
for an extent we release the destination path, free the ins_data array and
then return immediately. However a previous iteration of the for loop may
have added checksums to the ordered_sums list, in which case we leak the
memory used by them.
So fix this by making sure we iterate the ordered_sums list and free all
its checksums before returning.
Fixes: 3650860b90 ("Btrfs: remove almost all of the BUG()'s from tree-log.c")
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Chris Murphy reported a problem where rpm ostree will bind mount a bunch
of things for whatever voodoo it's doing. But when it does this
/proc/mounts shows something like
/dev/sda /mnt/test btrfs rw,relatime,subvolid=256,subvol=/foo 0 0
/dev/sda /mnt/test/baz btrfs rw,relatime,subvolid=256,subvol=/foo/bar 0 0
Despite subvolid=256 being subvol=/foo. This is because we're just
spitting out the dentry of the mount point, which in the case of bind
mounts is the source path for the mountpoint. Instead we should spit
out the path to the actual subvol. Fix this by looking up the name for
the subvolid we have mounted. With this fix the same test looks like
this
/dev/sda /mnt/test btrfs rw,relatime,subvolid=256,subvol=/foo 0 0
/dev/sda /mnt/test/baz btrfs rw,relatime,subvolid=256,subvol=/foo 0 0
Reported-by: Chris Murphy <chris@colorremedies.com>
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reported by Forza on IRC that remounting with compression options does
not reflect the change in level, or at least it does not appear to do so
according to the messages:
mount -o compress=zstd:1 /dev/sda /mnt
mount -o remount,compress=zstd:15 /mnt
does not print the change to the level to syslog:
[ 41.366060] BTRFS info (device vda): use zstd compression, level 1
[ 41.368254] BTRFS info (device vda): disk space caching is enabled
[ 41.390429] BTRFS info (device vda): disk space caching is enabled
What really happens is that the message is lost but the level is actualy
changed.
There's another weird output, if compression is reset to 'no':
[ 45.413776] BTRFS info (device vda): use no compression, level 4
To fix that, save the previous compression level and print the message
in that case too and use separate message for 'no' compression.
CC: stable@vger.kernel.org # 4.19+
Signed-off-by: David Sterba <dsterba@suse.com>
In try_to_merge_free_space we attempt to find entries to the left and
right of the entry we are adding to see if they can be merged. We
search for an entry past our current info (saved into right_info), and
then if right_info exists and it has a rb_prev() we save the rb_prev()
into left_info.
However there's a slight problem in the case that we have a right_info,
but no entry previous to that entry. At that point we will search for
an entry just before the info we're attempting to insert. This will
simply find right_info again, and assign it to left_info, making them
both the same pointer.
Now if right_info _can_ be merged with the range we're inserting, we'll
add it to the info and free right_info. However further down we'll
access left_info, which was right_info, and thus get a use-after-free.
Fix this by only searching for the left entry if we don't find a right
entry at all.
The CVE referenced had a specially crafted file system that could
trigger this use-after-free. However with the tree checker improvements
we no longer trigger the conditions for the UAF. But the original
conditions still apply, hence this fix.
Reference: CVE-2019-19448
Fixes: 9630308170 ("Btrfs: use hybrid extents+bitmap rb tree for free space")
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
[BUG]
There is a bug report of NULL pointer dereference caused in
compress_file_extent():
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Workqueue: btrfs-delalloc btrfs_delalloc_helper [btrfs]
NIP [c008000006dd4d34] compress_file_range.constprop.41+0x75c/0x8a0 [btrfs]
LR [c008000006dd4d1c] compress_file_range.constprop.41+0x744/0x8a0 [btrfs]
Call Trace:
[c000000c69093b00] [c008000006dd4d1c] compress_file_range.constprop.41+0x744/0x8a0 [btrfs] (unreliable)
[c000000c69093bd0] [c008000006dd4ebc] async_cow_start+0x44/0xa0 [btrfs]
[c000000c69093c10] [c008000006e14824] normal_work_helper+0xdc/0x598 [btrfs]
[c000000c69093c80] [c0000000001608c0] process_one_work+0x2c0/0x5b0
[c000000c69093d10] [c000000000160c38] worker_thread+0x88/0x660
[c000000c69093db0] [c00000000016b55c] kthread+0x1ac/0x1c0
[c000000c69093e20] [c00000000000b660] ret_from_kernel_thread+0x5c/0x7c
---[ end trace f16954aa20d822f6 ]---
[CAUSE]
For the following execution route of compress_file_range(), it's
possible to hit NULL pointer dereference:
compress_file_extent()
|- pages = NULL;
|- start = async_chunk->start = 0;
|- end = async_chunk = 4095;
|- nr_pages = 1;
|- inode_need_compress() == false; <<< Possible, see later explanation
| Now, we have nr_pages = 1, pages = NULL
|- cont:
|- ret = cow_file_range_inline();
|- if (ret <= 0) {
|- for (i = 0; i < nr_pages; i++) {
|- WARN_ON(pages[i]->mapping); <<< Crash
To enter above call execution branch, we need the following race:
Thread 1 (chattr) | Thread 2 (writeback)
--------------------------+------------------------------
| btrfs_run_delalloc_range
| |- inode_need_compress = true
| |- cow_file_range_async()
btrfs_ioctl_set_flag() |
|- binode_flags |= |
BTRFS_INODE_NOCOMPRESS |
| compress_file_range()
| |- inode_need_compress = false
| |- nr_page = 1 while pages = NULL
| | Then hit the crash
[FIX]
This patch will fix it by checking @pages before doing accessing it.
This patch is only designed as a hot fix and easy to backport.
More elegant fix may make btrfs only check inode_need_compress() once to
avoid such race, but that would be another story.
Reported-by: Luciano Chavez <chavez@us.ibm.com>
Fixes: 4d3a800ebb ("btrfs: merge nr_pages input and output parameter in compress_pages")
CC: stable@vger.kernel.org # 4.14.x: cecc8d9038d16: btrfs: Move free_pages_out label in inline extent handling branch in compress_file_range
CC: stable@vger.kernel.org # 4.14+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Pull misc vfs updates from Al Viro:
"No common topic whatsoever in those, sorry"
* 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
fs: define inode flags using bit numbers
iov_iter: Move unnecessary inclusion of crypto/hash.h
dlmfs: clean up dlmfs_file_{read,write}() a bit
-----BEGIN PGP SIGNATURE-----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=2vmy
-----END PGP SIGNATURE-----
Merge tag 'for-5.9/io_uring-20200802' of git://git.kernel.dk/linux-block
Pull io_uring updates from Jens Axboe:
"Lots of cleanups in here, hardening the code and/or making it easier
to read and fixing bugs, but a core feature/change too adding support
for real async buffered reads. With the latter in place, we just need
buffered write async support and we're done relying on kthreads for
the fast path. In detail:
- Cleanup how memory accounting is done on ring setup/free (Bijan)
- sq array offset calculation fixup (Dmitry)
- Consistently handle blocking off O_DIRECT submission path (me)
- Support proper async buffered reads, instead of relying on kthread
offload for that. This uses the page waitqueue to drive retries
from task_work, like we handle poll based retry. (me)
- IO completion optimizations (me)
- Fix race with accounting and ring fd install (me)
- Support EPOLLEXCLUSIVE (Jiufei)
- Get rid of the io_kiocb unionizing, made possible by shrinking
other bits (Pavel)
- Completion side cleanups (Pavel)
- Cleanup REQ_F_ flags handling, and kill off many of them (Pavel)
- Request environment grabbing cleanups (Pavel)
- File and socket read/write cleanups (Pavel)
- Improve kiocb_set_rw_flags() (Pavel)
- Tons of fixes and cleanups (Pavel)
- IORING_SQ_NEED_WAKEUP clear fix (Xiaoguang)"
* tag 'for-5.9/io_uring-20200802' of git://git.kernel.dk/linux-block: (127 commits)
io_uring: flip if handling after io_setup_async_rw
fs: optimise kiocb_set_rw_flags()
io_uring: don't touch 'ctx' after installing file descriptor
io_uring: get rid of atomic FAA for cq_timeouts
io_uring: consolidate *_check_overflow accounting
io_uring: fix stalled deferred requests
io_uring: fix racy overflow count reporting
io_uring: deduplicate __io_complete_rw()
io_uring: de-unionise io_kiocb
io-wq: update hash bits
io_uring: fix missing io_queue_linked_timeout()
io_uring: mark ->work uninitialised after cleanup
io_uring: deduplicate io_grab_files() calls
io_uring: don't do opcode prep twice
io_uring: clear IORING_SQ_NEED_WAKEUP after executing task works
io_uring: batch put_task_struct()
tasks: add put_task_struct_many()
io_uring: return locked and pinned page accounting
io_uring: don't miscount pinned memory
io_uring: don't open-code recv kbuf managment
...
-----BEGIN PGP SIGNATURE-----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=abJG
-----END PGP SIGNATURE-----
Merge tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block
Pull core block updates from Jens Axboe:
"Good amount of cleanups and tech debt removals in here, and as a
result, the diffstat shows a nice net reduction in code.
- Softirq completion cleanups (Christoph)
- Stop using ->queuedata (Christoph)
- Cleanup bd claiming (Christoph)
- Use check_events, moving away from the legacy media change
(Christoph)
- Use inode i_blkbits consistently (Christoph)
- Remove old unused writeback congestion bits (Christoph)
- Cleanup/unify submission path (Christoph)
- Use bio_uninit consistently, instead of bio_disassociate_blkg
(Christoph)
- sbitmap cleared bits handling (John)
- Request merging blktrace event addition (Jan)
- sysfs add/remove race fixes (Luis)
- blk-mq tag fixes/optimizations (Ming)
- Duplicate words in comments (Randy)
- Flush deferral cleanup (Yufen)
- IO context locking/retry fixes (John)
- struct_size() usage (Gustavo)
- blk-iocost fixes (Chengming)
- blk-cgroup IO stats fixes (Boris)
- Various little fixes"
* tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block: (135 commits)
block: blk-timeout: delete duplicated word
block: blk-mq-sched: delete duplicated word
block: blk-mq: delete duplicated word
block: genhd: delete duplicated words
block: elevator: delete duplicated word and fix typos
block: bio: delete duplicated words
block: bfq-iosched: fix duplicated word
iocost_monitor: start from the oldest usage index
iocost: Fix check condition of iocg abs_vdebt
block: Remove callback typedefs for blk_mq_ops
block: Use non _rcu version of list functions for tag_set_list
blk-cgroup: show global disk stats in root cgroup io.stat
blk-cgroup: make iostat functions visible to stat printing
block: improve discard bio alignment in __blkdev_issue_discard()
block: change REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL to be odd numbers
block: defer flush request no matter whether we have elevator
block: make blk_timeout_init() static
block: remove retry loop in ioc_release_fn()
block: remove unnecessary ioc nested locking
block: integrate bd_start_claiming into __blkdev_get
...
When removing an extent map at try_release_extent_mapping(), called through
the page release callback (btrfs_releasepage()), we always set the full
sync flag on the inode, which forces the next fsync to use a slower code
path.
This hurts performance for workloads that dirty an amount of data that
exceeds or is very close to the system's RAM memory and do frequent fsync
operations (like database servers can for example). In particular if there
are concurrent fsyncs against different files, by falling back to a full
fsync we do a lot more checksum lookups in the checksums btree, as we do
it for all the extents created in the current transaction, instead of only
the new ones since the last fsync. These checksums lookups not only take
some time but, more importantly, they also cause contention on the
checksums btree locks due to the concurrency with checksum insertions in
the btree by ordered extents from other inodes.
We actually don't need to set the full sync flag on the inode, because we
only remove extent maps that are in the list of modified extents if they
were created in a past transaction, in which case an fsync skips them as
it's pointless to log them. So stop setting the full fsync flag on the
inode whenever we remove an extent map.
This patch is part of a patchset that consists of 3 patches, which have
the following subjects:
1/3 btrfs: fix race between page release and a fast fsync
2/3 btrfs: release old extent maps during page release
3/3 btrfs: do not set the full sync flag on the inode during page release
Performance tests were ran against a branch (misc-next) containing the
whole patchset. The test exercises a workload where there are multiple
processes writing to files and fsyncing them (each writing and fsyncing
its own file), and in total the amount of data dirtied ranges from 2x to
4x the system's RAM memory (16GiB), so that the page release callback is
invoked frequently.
The following script, using fio, was used to perform the tests:
$ cat test-fsync.sh
#!/bin/bash
DEV=/dev/sdk
MNT=/mnt/sdk
MOUNT_OPTIONS="-o ssd"
MKFS_OPTIONS="-d single -m single"
if [ $# -ne 3 ]; then
echo "Use $0 NUM_JOBS FILE_SIZE FSYNC_FREQ"
exit 1
fi
NUM_JOBS=$1
FILE_SIZE=$2
FSYNC_FREQ=$3
cat <<EOF > /tmp/fio-job.ini
[writers]
rw=write
fsync=$FSYNC_FREQ
fallocate=none
group_reporting=1
direct=0
bs=64k
ioengine=sync
size=$FILE_SIZE
directory=$MNT
numjobs=$NUM_JOBS
thread
EOF
echo "Using config:"
echo
cat /tmp/fio-job.ini
echo
mkfs.btrfs -f $MKFS_OPTIONS $DEV &> /dev/null
mount $MOUNT_OPTIONS $DEV $MNT
fio /tmp/fio-job.ini
umount $MNT
The tests were performed for different numbers of jobs, file sizes and
fsync frequency. A qemu VM using kvm was used, with 8 cores (the host has
12 cores, with cpu governance set to performance mode on all cores), 16GiB
of ram (the host has 64GiB) and using a NVMe device directly (without an
intermediary filesystem in the host). While running the tests, the host
was not used for anything else, to avoid disturbing the tests.
The obtained results were the following, and the last line printed by
fio is pasted (includes aggregated throughput and test run time).
*****************************************************
**** 1 job, 32GiB file, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=29.1MiB/s (30.5MB/s), 29.1MiB/s-29.1MiB/s (30.5MB/s-30.5MB/s), io=32.0GiB (34.4GB), run=1127557-1127557msec
After patchset:
WRITE: bw=29.3MiB/s (30.7MB/s), 29.3MiB/s-29.3MiB/s (30.7MB/s-30.7MB/s), io=32.0GiB (34.4GB), run=1119042-1119042msec
(+0.7% throughput, -0.8% run time)
*****************************************************
**** 2 jobs, 16GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=33.5MiB/s (35.1MB/s), 33.5MiB/s-33.5MiB/s (35.1MB/s-35.1MB/s), io=32.0GiB (34.4GB), run=979000-979000msec
After patchset:
WRITE: bw=39.9MiB/s (41.8MB/s), 39.9MiB/s-39.9MiB/s (41.8MB/s-41.8MB/s), io=32.0GiB (34.4GB), run=821283-821283msec
(+19.1% throughput, -16.1% runtime)
*****************************************************
**** 4 jobs, 8GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=52.1MiB/s (54.6MB/s), 52.1MiB/s-52.1MiB/s (54.6MB/s-54.6MB/s), io=32.0GiB (34.4GB), run=629130-629130msec
After patchset:
WRITE: bw=71.8MiB/s (75.3MB/s), 71.8MiB/s-71.8MiB/s (75.3MB/s-75.3MB/s), io=32.0GiB (34.4GB), run=456357-456357msec
(+37.8% throughput, -27.5% runtime)
*****************************************************
**** 8 jobs, 4GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=76.1MiB/s (79.8MB/s), 76.1MiB/s-76.1MiB/s (79.8MB/s-79.8MB/s), io=32.0GiB (34.4GB), run=430708-430708msec
After patchset:
WRITE: bw=133MiB/s (140MB/s), 133MiB/s-133MiB/s (140MB/s-140MB/s), io=32.0GiB (34.4GB), run=245458-245458msec
(+74.7% throughput, -43.0% run time)
*****************************************************
**** 16 jobs, 2GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=74.7MiB/s (78.3MB/s), 74.7MiB/s-74.7MiB/s (78.3MB/s-78.3MB/s), io=32.0GiB (34.4GB), run=438625-438625msec
After patchset:
WRITE: bw=184MiB/s (193MB/s), 184MiB/s-184MiB/s (193MB/s-193MB/s), io=32.0GiB (34.4GB), run=177864-177864msec
(+146.3% throughput, -59.5% run time)
*****************************************************
**** 32 jobs, 2GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=72.6MiB/s (76.1MB/s), 72.6MiB/s-72.6MiB/s (76.1MB/s-76.1MB/s), io=64.0GiB (68.7GB), run=902615-902615msec
After patchset:
WRITE: bw=227MiB/s (238MB/s), 227MiB/s-227MiB/s (238MB/s-238MB/s), io=64.0GiB (68.7GB), run=288936-288936msec
(+212.7% throughput, -68.0% run time)
*****************************************************
**** 64 jobs, 1GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=98.8MiB/s (104MB/s), 98.8MiB/s-98.8MiB/s (104MB/s-104MB/s), io=64.0GiB (68.7GB), run=663126-663126msec
After patchset:
WRITE: bw=294MiB/s (308MB/s), 294MiB/s-294MiB/s (308MB/s-308MB/s), io=64.0GiB (68.7GB), run=222940-222940msec
(+197.6% throughput, -66.4% run time)
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When removing an extent map at try_release_extent_mapping(), called through
the page release callback (btrfs_releasepage()), we never release an extent
map that is in the list of modified extents. This is to prevent races with
a concurrent fsync using the fast path, which could lead to not logging an
extent created in the current transaction.
However we can safely remove an extent map created in a past transaction
that is still in the list of modified extents (because no one fsynced yet
the inode after that transaction got commited), because such extents are
skipped during an fsync as it is pointless to log them. This change does
that.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When releasing an extent map, done through the page release callback, we
can race with an ongoing fast fsync and cause the fsync to miss a new
extent and not log it. The steps for this to happen are the following:
1) A page is dirtied for some inode I;
2) Writeback for that page is triggered by a path other than fsync, for
example by the system due to memory pressure;
3) When the ordered extent for the extent (a single 4K page) finishes,
we unpin the corresponding extent map and set its generation to N,
the current transaction's generation;
4) The btrfs_releasepage() callback is invoked by the system due to
memory pressure for that no longer dirty page of inode I;
5) At the same time, some task calls fsync on inode I, joins transaction
N, and at btrfs_log_inode() it sees that the inode does not have the
full sync flag set, so we proceed with a fast fsync. But before we get
into btrfs_log_changed_extents() and lock the inode's extent map tree:
6) Through btrfs_releasepage() we end up at try_release_extent_mapping()
and we remove the extent map for the new 4Kb extent, because it is
neither pinned anymore nor locked. By calling remove_extent_mapping(),
we remove the extent map from the list of modified extents, since the
extent map does not have the logging flag set. We unlock the inode's
extent map tree;
7) The task doing the fast fsync now enters btrfs_log_changed_extents(),
locks the inode's extent map tree and iterates its list of modified
extents, which no longer has the 4Kb extent in it, so it does not log
the extent;
8) The fsync finishes;
9) Before transaction N is committed, a power failure happens. After
replaying the log, the 4K extent of inode I will be missing, since
it was not logged due to the race with try_release_extent_mapping().
So fix this by teaching try_release_extent_mapping() to not remove an
extent map if it's still in the list of modified extents.
Fixes: ff44c6e36d ("Btrfs: do not hold the write_lock on the extent tree while logging")
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When we're (re)mounting a btrfs filesystem we set the
BTRFS_FS_STATE_REMOUNTING state in fs_info to serialize against async
reclaim or defrags.
This flag is set in btrfs_remount_prepare() called by btrfs_remount().
As btrfs_remount_prepare() does nothing but setting this flag and
doesn't have a second caller, we can just open-code the flag setting in
btrfs_remount().
Similarly do for so clearing of the flag by moving it out of
btrfs_remount_cleanup() into btrfs_remount() to be symmetrical.
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Previously we depended on some weird behavior in our chunk allocator to
force the allocation of new stripes, so by the time we got to doing the
reduce we would usually already have a chunk with the proper target.
However that behavior causes other problems and needs to be removed.
First however we need to remove this check to only restripe if we
already have those available profiles, because if we're allocating our
first chunk it obviously will not be available. Simply use the target
as specified, and if that fails it'll be because we're out of space.
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
btrfs/061 has been failing consistently for me recently with a
transaction abort. We run out of space in the system chunk array, which
means we've allocated way too many system chunks than we need.
Chris added this a long time ago for balance as a poor mans restriping.
If you had a single disk and then added another disk and then did a
balance, update_block_group_flags would then figure out which RAID level
you needed.
Fast forward to today and we have restriping behavior, so we can
explicitly tell the fs that we're trying to change the raid level. This
is accomplished through the normal get_alloc_profile path.
Furthermore this code actually causes btrfs/061 to fail, because we do
things like mkfs -m dup -d single with multiple devices. This trips
this check
alloc_flags = update_block_group_flags(fs_info, cache->flags);
if (alloc_flags != cache->flags) {
ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
in btrfs_inc_block_group_ro. Because we're balancing and scrubbing, but
not actually restriping, we keep forcing chunk allocation of RAID1
chunks. This eventually causes us to run out of system space and the
file system aborts and flips read only.
We don't need this poor mans restriping any more, simply use the normal
get_alloc_profile helper, which will get the correct alloc_flags and
thus make the right decision for chunk allocation. This keeps us from
allocating a billion system chunks and falling over.
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Nikolay Borisov